Triple
T16854450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Advertising agency |
E409749
|
entity |
| Predicate | mayBeTypeOf |
P114972
|
FINISHED |
| Object | full-service agency |
—
|
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: full-service agency | Statement: [Advertising agency, mayBeTypeOf, full-service agency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayBeTypeOf Context triple: [Advertising agency, mayBeTypeOf, full-service agency]
-
A.
canBeTypeOf
Indicates that one entity is capable of serving as, or being classified as, a particular type or category of another entity.
-
B.
fulfillsTypeOf
Indicates that one entity satisfies or conforms to a specified type, category, or classification defined by another entity.
-
C.
typeOf
Indicates that one entity is a specific kind, class, or category instance of another more general entity.
-
D.
possibleTypeOfReferent
chosen
Indicates that something could be a potential or candidate type or category to which a given referent may belong, without asserting that it definitively is that type.
-
E.
mayBeEqualTo
Indicates that two entities are possibly equal, but their equality is uncertain or not definitively established.
- 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_69d88395e6c88190b22730f335107c14 |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b37c6e808190975b14b228253029 |
completed | April 18, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69e32b8cbb048190878a259cc5be960e |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:24 a.m.