Triple
T8620811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Andrews |
E204157
|
entity |
| Predicate | creditType |
P41710
|
FINISHED |
| Object | on-screen cinematography credit |
—
|
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: on-screen cinematography credit | Statement: [Peter Andrews, creditType, on-screen cinematography credit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: creditType Context triple: [Peter Andrews, creditType, on-screen cinematography credit]
-
A.
cardType
Indicates the classification or category assigned to a card within a given system or context.
-
B.
creditFlexibility
Indicates that one party allows adaptable or negotiable credit terms, limits, or repayment conditions for another party.
-
C.
includesCreditCategory
Indicates that one entity contains or encompasses a specific credit-related category within its defined set or structure.
-
D.
collateralType
Indicates the kind or category of collateral associated with an obligation, agreement, or financial exposure.
-
E.
requiresCreditAs
chosen
Indicates that one entity must be credited or acknowledged in a specified manner or role in relation to 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_69ca832ceab8819096e4a9f546695079 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc5730309081909a9a0256c9bf5f8f |
completed | March 31, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69cc455906f8819082edd79cb4a1cf28 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:26 p.m.