Triple
T9899652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SOC 1 |
E182251
|
entity |
| Predicate | reportIssuer |
P64616
|
FINISHED |
| Object | independent CPA firm |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: independent CPA firm | Statement: [SOC 1, reportIssuer, independent CPA firm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reportIssuer Context triple: [SOC 1, reportIssuer, independent CPA firm]
-
A.
reportPublisher
Indicates that one entity is the organization or individual responsible for publishing a given report.
-
B.
issuerProduces
chosen
Indicates that an issuer creates, generates, or brings into existence a particular product, document, asset, or item.
-
C.
typicalIssuer
Indicates that one entity is the standard or commonly expected issuer (e.g., of a document, instrument, or credential) for another entity.
-
D.
reportsThrough
Indicates that one entity formally communicates and is accountable to another entity through an established reporting or supervisory chain.
-
E.
targetIssuerProfile
Indicates a relationship where a specific profile is designated as the primary or intended issuer in a given context.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca82876f8081909cf75df0f99bb13f |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb4adc03481909e0f657db01e5bab |
completed | April 2, 2026, 12:13 a.m. |
| PD | Predicate disambiguation | batch_69cd1d872d50819096b7ab166a8decf1 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:40 p.m.