Someone will ask you to defend a merge. 64 entity resolution terms, so you can.
- terms, each with a definition and a page of its own
- 64
- shelves, grouped by what you are trying to settle
- 7
- cross-references between terms, every one checked when the site builds
- 339
- when the figures inside these definitions were last read off the product repository
- 2026-09-05
Every term is also a page of its own: the full definition, the related terms, and where the idea shows up in the running product.
On this page
A–Z
Every term, alphabetically, linking to its own page. The seven shelves below hold the same terms with their definitions, filed by what you are trying to settle.
Foundations
What the problem is called, and what the objects in it are. Entity, record, cluster, and the four industry names for the same job.
Entity resolution
Entity resolution is the process of deciding which records, across one or many datasets, refer to the same real-world thing — and, when the evidence does not settle it, deciding that too.
Record linkage
Record linkage is the classical statistical name for joining records that refer to the same entity across two or more files with no shared key.
Deduplication
Deduplication is entity resolution applied within a single dataset: finding the rows that are the same thing and deciding which of them may safely be collapsed.
Entity
An entity is the real-world thing a set of records is asserted to describe — in Entity Bind, one company or organisation, holding a stable identifier that survives the records attaching to it.
Record
A record is one observation of an entity from one source at one time — the unit that arrives, is compared and is attached, never the unit that is trusted on its own.
Cluster
A cluster is the set of records a resolver has decided belong to one entity, and the object that cluster-level metrics are scored against.
Golden record
A golden record is the single assembled view of an entity built by choosing one value per field from the records attached to it, ideally with the provenance of each choice carried alongside it.
Survivorship
Survivorship is the set of rules that picks which value wins, field by field, when the records in a cluster disagree.
Master data management (MDM)
Master data management is the organisational discipline and the platform category that maintains authoritative shared records for core business objects such as customers, suppliers and products.
Reference data
Reference data is the slow-changing, externally defined data used to classify and identify things — registers, code lists, identifier schemes — as opposed to the transactional data that refers to it.
Once the vocabulary is settled, the question underneath it is which of your own rows are the same company. That one takes a file.
Start freeMatching methods
How two records are compared and how the comparison is made cheap enough to run. Blocking, deterministic rules, probabilistic scoring, string distance.
Normalisation
Normalisation rewrites a record into a comparable form — case, punctuation, legal forms, identifier shapes — before any comparison is attempted, and it is where most of the achievable accuracy in entity resolution is won or lost.
Transliteration
Transliteration maps text from one writing system into another — Cyrillic or Greek or Han into Latin script — so that names recorded in different alphabets can be compared at all.
Blocking
Blocking is the technique that makes entity resolution affordable by comparing each record only against a small set of plausible candidates instead of against every other record.
Candidate generation
Candidate generation is the retrieval step that proposes the small set of entities a record might be, and its recall is the hard ceiling on everything the rest of the pipeline can achieve.
Deterministic matching
Deterministic matching decides a pair by an explicit rule — usually agreement on a strong identifier — and produces the same verdict every time with no score in between.
Probabilistic matching
Probabilistic matching scores a candidate pair by weighing the agreement and disagreement of several fields into a single number, then applies thresholds to that number rather than to any one field.
Fellegi–Sunter
Fellegi–Sunter is the 1969 statistical framework for record linkage that scores a candidate pair as a log-likelihood ratio of field agreements and splits the result into three regions: accept, reject, and refer for review.
m-probability
The m-probability of a comparison field is the probability that the field agrees given that the pair really is a match — in effect, one minus the rate at which that field is wrong, missing or mistyped in true matches.
u-probability
The u-probability of a comparison field is the probability that the field agrees by chance given that the pair is not a match — a measure of how common a value is, and therefore of how little an agreement proves.
Match weight
A match weight is the log-scaled contribution one comparison makes to a pair's score, positive when agreement is evidence of a match and negative when disagreement is evidence against.
Fuzzy matching
Fuzzy matching compares strings by similarity rather than equality, returning a score between zero and one — a useful retrieval signal and, on its own, not a calibrated basis for a merge.
Edit distance
Edit distance counts the minimum number of single-character insertions, deletions or substitutions needed to turn one string into another; Levenshtein distance is the standard form.
Jaro–Winkler
Jaro–Winkler is a string similarity measure that scores character agreement within a sliding window and then boosts pairs sharing a common prefix, which makes it well suited to names and poorly suited to truncation.
Measurement
How you tell whether any of it worked, and which numbers may not be quoted without which other numbers.
Precision
Precision is the share of the matches a system asserted that were correct — and it is meaningless without the share of records the system was willing to decide at all.
Recall
Recall is the share of the true matches present in the data that a system actually found, and it is the metric that abstention costs you.
F1 score
F1 is the harmonic mean of precision and recall, reported as a single number that is only interpretable once you know which of its two components is doing the work.
B-cubed (B³)
B-cubed is a cluster-level evaluation metric that scores precision and recall from the point of view of each individual record, asking what share of its assigned cluster genuinely belongs with it and what share of its true family it was placed with.
Pairwise metrics
Pairwise metrics evaluate a resolver one candidate pair at a time — did it correctly decide that these two records are or are not the same entity — and they systematically flatter systems whose errors chain together.
Cluster metrics
Cluster metrics evaluate the groups a resolver produced rather than the pairs it judged, which is the only way to see errors that only appear once pairwise decisions are chained into entities.
Recall@k
Recall@k is the share of records for which the correct entity appears anywhere in the top k candidates returned by retrieval, and it is the ceiling on everything a matcher downstream can get right.
Calibration
A confidence score is calibrated when it matches observed reality — of the decisions returned at 0.95, about 95% should be correct — which is a different property from being accurate, and a much rarer one.
Expected calibration error (ECE)
Expected calibration error summarises miscalibration as the average gap between stated confidence and observed accuracy across confidence buckets, weighted by how many predictions fall in each.
Wilson interval
The Wilson score interval is a confidence interval for a proportion that stays sensible at the extremes, which is why it is the right interval to publish when a system has made no observed errors at all.
False positive
A false positive in entity resolution is a pair of records asserted to be the same entity when they are not — the error class that corrupts data rather than merely leaving it untidy.
False bind
A false bind is Entity Bind's name for the error it treats as unacceptable: a record attached to the wrong company entity and returned as a decided match.
Over-merge
An over-merge is a cluster containing records from more than one real entity — the failure that turns two customers, two suppliers or two counterparties into one.
Fragmentation
Fragmentation is the opposite failure to over-merging: one real entity split across several clusters, so the same company is counted, contracted with or invoiced more than once.
Decisions and evidence
What the system returns, what it refuses to return, and what a decision can be redeemed for afterwards.
Confidence floor
A confidence floor is the score below which a system refuses to return a match at all, expressed as an acceptance contract rather than as a promise about accuracy.
Abstention
An abstention is a first-class 'we do not know' returned instead of a match: the record comes back unresolved, with a ranked shortlist, a typed reason and the column that would have decided it.
Review queue
A review queue is where records the system refused to decide are held for a human, and the quality of a resolver is largely determined by how small, how well-evidenced and how accountable that queue is.
Decision receipt
A decision receipt is the durable, retrievable record of why a particular match was made — the features, the probability, the thresholds in force, the sources cited and the version of the pipeline that decided — addressable by an identifier returned with the answer.
Provenance
Provenance is the record of where each individual value came from — which source, retrieved when, effective when — attached to the value itself rather than to the dataset as a whole.
Citation
A citation is a resolvable pointer to the specific source document or record that supports a claim, as distinct from a source name, which is only an attribution.
Idempotency
An operation is idempotent when performing it repeatedly has the same effect as performing it once, which is what makes a retry after a timeout safe rather than duplicating work.
Replay
Replay is re-serving a previous decision for byte-identical content rather than recomputing it, which makes repeated submissions free and deterministic — provided the replayed decision is still one the system would stand behind.
Content fingerprint
A content fingerprint is a hash of the meaningful content of a submitted record, used to recognise that the same thing has been sent before regardless of when, in what order, or under what key.
Data, licence and time
Facts have owners and dates. What may be stored, what may only be passed through, and what a date on a fact actually asserts.
Licence tier
A licence tier is the classification carried by an individual fact that determines what may lawfully be done with it — stored, redistributed, resold, or only shown once to the caller who asked.
Pass-through data
Pass-through data is material a system may return to the caller who asked for it but may never retain — the tier where the difference between showing and storing is contractual rather than stylistic.
Temporal facts
A temporal fact is a value stored with the period over which it was true and the history of when it was observed, rather than as a single current value that silently overwrites its predecessor.
First seen
First seen is the timestamp at which a system first observed a fact, which is evidence about the system's own history and not about when the fact became true.
Last confirmed
Last confirmed is the most recent time a fact was observed still to hold, which is the freshness signal a golden record should rank on and a weaker claim than 'currently true'.
PSC (person with significant control)
A PSC is a person or corporate body with significant control over a UK company — broadly, more than 25% of shares or voting rights, or the right to appoint or remove the majority of the board — declared to Companies House and published on the register.
Beneficial ownership
Beneficial ownership is the question of which natural persons ultimately own or control a company, as distinct from the legal owners recorded on its share register.
Identifiers
The keys company data is joined on, who issues each one, and where each stops being unique.
Crosswalk
A crosswalk is a mapping between the identifier schemes that name the same company in different systems — LEI to company number to CIK to ticker — so that data joined on one key can be joined to data keyed on another.
LEI (Legal Entity Identifier)
The LEI is a 20-character ISO 17442 code identifying a legal entity that participates in financial transactions, issued through the Global LEI Foundation and published as open reference data.
Company number
A company number is the identifier a register assigns to a company at incorporation, and it is unique only within the register that issued it — never within a country and never globally.
CIK (Central Index Key)
The CIK is the number the US Securities and Exchange Commission assigns to every filer in its EDGAR system, and it is the join key for anything derived from US securities filings.
Ticker symbol
A ticker is the short code identifying a security on a particular exchange — a property of a listing rather than of a company, and unambiguous only once the exchange is named.
SIREN and SIRET
SIREN is the nine-digit identifier France assigns to a legal unit and SIRET is the fourteen-digit identifier of one of its establishments — the same company at two different levels of granularity.
D-U-N-S number
The D-U-N-S number is a nine-digit identifier assigned by a commercial data provider to business establishments worldwide, and it is proprietary: it can be matched on and cannot be derived from open data.
EUID (European Unique Identifier)
The EUID is the identifier assigned under the EU Business Registers Interconnection System, combining a country code, a register code and the national registration number into one pan-European key.
VAT number
A VAT number is a tax registration identifier issued by a national tax authority, checkable against the EU's validation service for member states, and a strong but imperfect proxy for company identity.
A company number or an LEI settles a row at the cheapest stage of the cascade; a bare name has further to travel. Start on Free with your own CSV, then choose a paid plan in Billing when its columns require deeper checks.
Start freeInterfaces
How a program or an agent reaches a resolver, and what a call costs.
MCP (Model Context Protocol)
The Model Context Protocol is an open standard for connecting AI assistants to external tools and data, so that a model can call a system's real operations instead of being told about them in a prompt.
Tool call
A tool call is a single invocation of an exposed operation by a model or agent, with structured arguments and a structured result — the unit that is authenticated, metered and audited.
Built for a company master you have to defend
The vocabulary above is free to anyone who wants it. The product underneath it suits one job better than the others, and two lines decide most of that.
Teams with a company master they have to defend — an MDM or stewardship queue, a CRM after a migration or a merger, a supplier file before a payment run, or counterparty onboarding that has to survive an audit.
Buying breadth as the product: we hold a fraction of an incumbent’s records and are not building a global company graph. Entity Bind resolves companies and organisations only. It does not resolve people, vessels, bank-account ownership, sanctions exposure, emissions or geolocation, and its results may not be used for eligibility decisions about individuals, including employment, credit and tenancy.
The retention, erasure and tenancy detail a security review asks for is on the trust page, with where assurance stands: no SOC 2, no external validation of the accuracy figures, no customer holdout. Trust and security →
Four of these are things we do not do
Entity Bind does not estimate m and u separately, does not publish an expected calibration error, and cannot issue a D-U-N-S number — only its commercial issuer assigns those. All four are defined here in full, and each term's page says what happens instead.
- m-probability
The m-probability of a comparison field is the probability that the field agrees given that the pair really is a match — in effect, one minus the rate at which that field is wrong, missing or mistyped in true matches.
- u-probability
The u-probability of a comparison field is the probability that the field agrees by chance given that the pair is not a match — a measure of how common a value is, and therefore of how little an agreement proves.
- Expected calibration error (ECE)
Expected calibration error summarises miscalibration as the average gap between stated confidence and observed accuracy across confidence buckets, weighted by how many predictions fall in each.
- D-U-N-S number
The D-U-N-S number is a nine-digit identifier assigned by a commercial data provider to business establishments worldwide, and it is proprietary: it can be matched on and cannot be derived from open data.
Every rate on the accuracy page carries the fixture it was measured on, the fraction behind it and the interval around it.
Read the accuracy methodInternal fixtures only. The historical 2026-08-29 per-tier recording covers 317 GB companies with identifier-rich arrivals seeding the catalogue first; the context tier includes country and registered-town prose. Its legacy replay has no full-prompt-verified calls and cannot certify current calibration. The September 5 CI reports cover 1,176 labelled pairs and 705 records over 250 companies using offline stubs. These are not independent customer holdouts or live production validation; the 99% minimum-input product target remains unmet. Scope is company and organisation identity only — not people, vessels, bank-account ownership, sanctions or emissions. Results may not be used for eligibility decisions about individuals, including employment, credit and tenancy.
Where a definition stops being enough
A term page routes into the product. This is the other direction: three families that take a word and make it long enough to act on.
- Where a definition becomes a methodLong-form method: blocking and candidate generation, Fellegi–Sunter, calibration, survivorship, and how to measure any of it on your own file.Open
- The definitions this vocabulary leaves outWhich of the identifier columns already in your file settle a match on their own, who issues each one, the exact shape a value takes, and what goes wrong with it.Open
- The decision behind the wordThe jobs this gets bought for, what breaks in each one today, and what the wrong merge costs to unwind once it has been made.Open
Start with your own company records.
Create your workspace, verify your email and run your first company file. The Free plan needs no card. Create API keys in your workspace when you need an integration.
300 credits. No card.
For a guided review of your file, explore the Merge Safety Sprint →