Triple
T35182164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Big Knife (Broadway revival) |
E1015881
|
entity |
| Predicate | hasOriginalPlaywright |
P197889
|
FINISHED |
| Object | Clifford Odets |
—
|
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: Clifford Odets | Statement: [The Big Knife (Broadway revival), hasOriginalPlaywright, Clifford Odets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOriginalPlaywright Context triple: [The Big Knife (Broadway revival), hasOriginalPlaywright, Clifford Odets]
-
A.
hasOriginalWebPilot
Indicates that an entity is associated with or linked to its original WebPilot instance or source.
-
B.
hasOriginalProducer
Indicates that an entity was initially created, manufactured, or produced by a specific producer or organization.
-
C.
hasOriginalVersion
Indicates that one entity is the original or initial version from which another entity is derived or adapted.
-
D.
hasOriginalWorkSetting
Indicates that an entity is associated with the setting or context in which the original work or source material takes place.
-
E.
hasOriginalRole
Indicates that an entity previously held a particular role or function before a change to its current role.
- F. None of above. chosen
Provenance (4 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_69f76ddcc108819097f96853b7ed9ef4 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69feb5e66224819083b87c3707a5a5e0 |
completed | May 9, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69feb3bd700c8190991ed200cd3c04db |
completed | May 9, 2026, 4:10 a.m. |
| PDg | Predicate description generation | batch_69feb5e50a7481908d6bff55bd85e06d |
completed | May 9, 2026, 4:19 a.m. |
Created at: May 3, 2026, 4:02 p.m.