Triple
T35704394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bash Howard |
E1031675
|
entity |
| Predicate | productionRoleInPlot |
P49052
|
FINISHED |
| Object | financier of GLOW promotion |
—
|
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: financier of GLOW promotion | Statement: [Bash Howard, productionRoleInPlot, financier of GLOW promotion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: productionRoleInPlot Context triple: [Bash Howard, productionRoleInPlot, financier of GLOW promotion]
-
A.
producerRole
chosen
Indicates that an entity serves in the role of producer for another entity, such as a work, product, or event.
-
B.
producesRole
Indicates that one entity generates, creates, or gives rise to a particular role associated with another entity.
-
C.
producedRole
Indicates that one entity was responsible for creating, originating, or bringing about a particular role associated with another entity.
-
D.
producerCharacter
Indicates that a producer is responsible for or associated with a particular character in a work.
-
E.
roleInFilmProduction
Indicates the specific function or responsibility an entity has within the making of a film.
- 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_69f76e0d393c8190b6303c64408736db |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fed83b1d188190a318b0ad3003200a |
completed | May 9, 2026, 6:46 a.m. |
| PD | Predicate disambiguation | batch_69fed78e03548190b6e6ad93ae8d131d |
completed | May 9, 2026, 6:43 a.m. |
Created at: May 3, 2026, 4:05 p.m.