Triple
T37790657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucie de Mirecourt |
E942076
|
entity |
| Predicate | hasCastMemberInWork |
P201885
|
FINISHED |
| Object | Josephine Baker |
—
|
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: Josephine Baker | Statement: [Lucie de Mirecourt, hasCastMemberInWork, Josephine Baker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCastMemberInWork Context triple: [Lucie de Mirecourt, hasCastMemberInWork, Josephine Baker]
-
A.
hasHumanCast
Indicates that a work or production features human performers as part of its cast.
-
B.
hasCrewMember
Indicates that an entity includes or employs another entity as a member of its crew.
-
C.
hasRelativeInCastOrCrew
Indicates that at least one member of a work’s cast or crew is a relative of a specified person.
-
D.
hasCastOrCrew
Indicates that an entity (such as a film or show) is associated with one or more people who are part of its cast or crew.
-
E.
relatedCastMember
Indicates that two cast members are connected through a relevant relationship, such as working together on the same production or being otherwise professionally associated.
- 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_69f76ee5cb0c81909a363d1c929156c0 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a002e71bdc48190b922f2d3b362d259 |
completed | May 10, 2026, 7:06 a.m. |
| PD | Predicate disambiguation | batch_6a002e1a28708190b65f9e657c770bab |
completed | May 10, 2026, 7:04 a.m. |
| PDg | Predicate description generation | batch_6a002e706dfc8190bbf2bc230f537e83 |
completed | May 10, 2026, 7:06 a.m. |
Created at: May 3, 2026, 4:19 p.m.