Triple
T33201704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yaaro Yaarodi |
E849916
|
entity |
| Predicate | filmDirectorOfFeaturedWork |
P106734
|
FINISHED |
| Object | Mani Ratnam |
—
|
NE NERFINISHED |
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: Mani Ratnam | Statement: [Yaaro Yaarodi, filmDirectorOfFeaturedWork, Mani Ratnam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmDirectorOfFeaturedWork Context triple: [Yaaro Yaarodi, filmDirectorOfFeaturedWork, Mani Ratnam]
-
A.
filmDirectorOfFeaturingWork
Indicates that a person is the director of a film in which a particular work (such as a book, play, or other source material) is featured or adapted.
-
B.
filmDirectorOfAssociatedWork
Indicates that a person serves as the director of the specified creative work (such as a film or related audiovisual production).
-
C.
filmDirectorOfWorkAppearsIn
chosen
Indicates that a person is the director of a film in which a particular work (e.g., book, play, or other source material) appears or is featured.
-
D.
filmDirectorOfAwardedWork
Indicates that a person directed a film that has received an award.
-
E.
directorOfWorkFeaturingSubject
Indicates that the subject is the director of a creative work in which another specified entity appears or is featured.
- 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_69f3495efedc8190843a5728089544b9 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6e02ba6b881908dfafc52d3b75f1c |
completed | May 3, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69f6de09c2f481909f8b2545d3208c9f |
completed | May 3, 2026, 5:32 a.m. |
Created at: May 1, 2026, 1:30 a.m.