Triple
T27122447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lydia Bennet (Pride and Prejudice, 1940 film) |
E687036
|
entity |
| Predicate | hasGenreOfSourceWork |
P61875
|
FINISHED |
| Object | romantic drama |
—
|
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: romantic drama | Statement: [Lydia Bennet (Pride and Prejudice, 1940 film), hasGenreOfSourceWork, romantic drama]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGenreOfSourceWork Context triple: [Lydia Bennet (Pride and Prejudice, 1940 film), hasGenreOfSourceWork, romantic drama]
-
A.
hasGenreOfWorkItAppearsIn
Indicates that an entity is associated with the genre of the work in which it appears.
-
B.
hasSourceMaterialGenre
chosen
Indicates that the genre of the source material from which something is derived is specified.
-
C.
belongsToWorkGenre
Indicates that a creative work is classified under or associated with a particular genre.
-
D.
hasGenreRelation
Indicates that there is an association between an entity and a specific genre, specifying the type or category it belongs to.
-
E.
hasGenreOfClaim
Indicates that a claim is categorized or classified under a particular genre or type of claim.
- 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_69ef148c2b588190afc15b529f7af845 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f6cee45590819086e489bfccbe4ac3 |
completed | May 3, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1188708190b8f0f56e595e6057 |
completed | May 3, 2026, 4:16 a.m. |
Created at: April 27, 2026, 9 a.m.