Triple
T29734457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean Ogilvie |
E752416
|
entity |
| Predicate | workCastMember |
P74774
|
FINISHED |
| Object | Sydney Greenstreet |
—
|
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: Sydney Greenstreet | Statement: [Jean Ogilvie, workCastMember, Sydney Greenstreet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workCastMember Context triple: [Jean Ogilvie, workCastMember, Sydney Greenstreet]
-
A.
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.
-
B.
hasCrewMember
Indicates that an entity includes or employs another entity as a member of its crew.
-
C.
castMemberWith
chosen
Indicates that one entity is a cast member appearing together with another specified entity in the same production or work.
-
D.
laterCastMember
Indicates that one entity joined the cast of a show, film, or production at a later time than another cast member.
-
E.
includesCastMembersFrom
Indicates that one entity’s cast list contains one or more cast members who also appear in the cast list of another 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_69f0d62a36a88190bf860f00da433ff8 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f6733385a081909bea1257ca0b490e |
completed | May 2, 2026, 9:57 p.m. |
| PD | Predicate disambiguation | batch_69f66ec5bf508190ad088b89455252bd |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 28, 2026, 7:44 p.m.