Triple
T34357424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian De Palma and Paul Schrader |
E881770
|
entity |
| Predicate | sharesProfessionalCircleWith |
P133092
|
FINISHED |
| Object | Martin Scorsese |
—
|
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: Martin Scorsese | Statement: [Brian De Palma and Paul Schrader, sharesProfessionalCircleWith, Martin Scorsese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesProfessionalCircleWith Context triple: [Brian De Palma and Paul Schrader, sharesProfessionalCircleWith, Martin Scorsese]
-
A.
sharesProfessionWith
Indicates that two entities have the same profession or occupational role.
-
B.
socialCircle
Indicates that one entity belongs to, or is part of, the group of people with whom another entity regularly interacts socially.
-
C.
sharesArtisticCircleWith
chosen
Indicates that two individuals are part of the same artistic community, network, or circle of collaborators.
-
D.
sharesCommunityWith
Indicates that two entities belong to or participate in the same community or communal group.
-
E.
sharesWorkplaceWith
Indicates that two entities work at the same workplace or organization.
- 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_69f349bd06008190904c2f86c42749e3 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a000a1d8fa88190a1d82ac746565c48 |
completed | May 10, 2026, 4:31 a.m. |
| PD | Predicate disambiguation | batch_6a0008b26eb88190ae03b2309a614774 |
completed | May 10, 2026, 4:25 a.m. |
Created at: May 1, 2026, 1:58 a.m.