Triple
T21436463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battlecreek |
E528824
|
entity |
| Predicate | hasDirectorGender |
P143945
|
FINISHED |
| Object | female director |
—
|
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: female director | Statement: [Battlecreek, hasDirectorGender, female director]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectorGender Context triple: [Battlecreek, hasDirectorGender, female director]
-
A.
hasDirectorStar
Indicates that a person both directed and starred in the same work (e.g., film, show, or production).
-
B.
hasLeadCharacterGender
Indicates that the primary or lead character in a work has a specified gender.
-
C.
hasDirectorOfWork
Indicates that an entity has a specific person or organization serving as the director responsible for overseeing its work or project.
-
D.
hasDirectorNationality
Indicates that the nationality of a director is associated with a given entity (such as a film, organization, or work).
-
E.
isDirectedBy
Indicates that one entity serves as the director or guiding authority responsible for the creation, management, or execution of another entity (such as a film, project, or organization).
- F. None of above. chosen
Provenance (4 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_69e0c4569fa081908101baa24f8745db |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b537f39081909220577618657805 |
completed | April 22, 2026, 11:47 a.m. |
| PD | Predicate disambiguation | batch_69e61639ee288190889ffd500d1260f6 |
completed | April 20, 2026, 12:04 p.m. |
| PDg | Predicate description generation | batch_69e6190163448190a2404b396215c686 |
completed | April 20, 2026, 12:16 p.m. |
Created at: April 16, 2026, 6:02 p.m.