Triple
T30708993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Countess de Premilly (disputed/claimed) |
E781836
|
entity |
| Predicate | claimantOccupation |
P66757
|
FINISHED |
| Object | socialite |
—
|
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: socialite | Statement: [Countess de Premilly (disputed/claimed), claimantOccupation, socialite]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: claimantOccupation Context triple: [Countess de Premilly (disputed/claimed), claimantOccupation, socialite]
-
A.
allegedOccupation
chosen
Indicates that one entity is claimed or reported to be the occupation or job role of another entity, without asserting that this claim is necessarily true.
-
B.
subjectOccupation
Indicates that the subject holds or performs a particular job, profession, or role as their occupation.
-
C.
holderIsOccupation
Indicates that the holder entity has the specified occupation or job role.
-
D.
proposerOccupation
Indicates the occupation or professional role held by the entity acting as the proposer in a given context.
-
E.
recipientOccupation
Indicates that the object specifies the job, profession, or role held by the recipient in the described relationship or event.
- 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_69f224abfcf081909492e64d3cc35262 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f73ae120bc8190bff94d38d7a7a00d |
completed | May 3, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69f73a38d0848190aa5139144b8561c6 |
completed | May 3, 2026, 12:06 p.m. |
Created at: April 29, 2026, 8:35 p.m.