Triple
T26805321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terence McCloy |
E671818
|
entity |
| Predicate | screenplayCreditFor |
P135982
|
FINISHED |
| Object | Lady Sings the Blues |
—
|
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: Lady Sings the Blues | Statement: [Terence McCloy, screenplayCreditFor, Lady Sings the Blues]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenplayCreditFor Context triple: [Terence McCloy, screenplayCreditFor, Lady Sings the Blues]
-
A.
screenplayCredit
chosen
Indicates that one entity is credited for writing or contributing to the screenplay of another entity (typically a film, episode, or similar work).
-
B.
screenwriterCreditContext
Indicates the contextual details or circumstances under which a person is credited as a screenwriter for a particular work.
-
C.
screenwriterOfWorkFeaturing
Indicates that one entity is the screenwriter responsible for creating the screenplay for a work in which the other entity appears or is featured.
-
D.
screenwriterOfWorkAppearingIn
Indicates that a person is the screenwriter of a work in which a specified entity (such as a character, actor, or role) appears.
-
E.
screenwriterOfWorkAppearsIn
Indicates that a person is the screenwriter of a work in which they themselves also appear.
- 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_69eeb3225a3c8190aaf6746efeded2f3 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61a1c3b5081908b78ae264c66ffcc |
completed | May 2, 2026, 3:37 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 4:25 a.m.