Triple
T27987375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portraits of Jean Cocteau |
E706778
|
entity |
| Predicate | creatorHasOccupation |
P105981
|
FINISHED |
| Object | photographer |
—
|
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: photographer | Statement: [Portraits of Jean Cocteau, creatorHasOccupation, photographer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: creatorHasOccupation Context triple: [Portraits of Jean Cocteau, creatorHasOccupation, photographer]
-
A.
holderIsOccupation
chosen
Indicates that the holder entity has the specified occupation or job role.
-
B.
hasOccupationOfDesignee
Indicates that one entity serves as the designated or appointed holder of an occupation or role for another entity.
-
C.
recognizedOccupationOf
Indicates that one entity is acknowledged or officially accepted as the occupation or professional role held by another entity.
-
D.
hasOccupationInReality
Indicates that an entity holds or performs a specific occupation in the real world, as opposed to fictional or hypothetical contexts.
-
E.
ownerProfession
Indicates that the profession or occupation is associated with, or held by, the owner of a specified entity.
- 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_69ef96b8b8d88190bad5e4ae966bf14e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f7b0e5744c8190a22c1e1d6fcfa466 |
completed | May 3, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f7ab70d034819080295628497d8582 |
completed | May 3, 2026, 8:09 p.m. |
Created at: April 27, 2026, 7:48 p.m.