Triple
T26617663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David R. Ellis |
E668105
|
entity |
| Predicate | stuntCoordinatorOn |
P161053
|
FINISHED |
| Object | Scarface (1983 film) |
—
|
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: Scarface (1983 film) | Statement: [David R. Ellis, stuntCoordinatorOn, Scarface (1983 film)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stuntCoordinatorOn Context triple: [David R. Ellis, stuntCoordinatorOn, Scarface (1983 film)]
-
A.
hasStuntDouble
Indicates that one entity serves as a stunt double who performs dangerous or physically demanding actions on behalf of another entity.
-
B.
leadActorPerformedOwnStunts
Indicates that the lead actor personally carried out the stunts in the production rather than using a stunt double.
-
C.
rescueCoordinatedBy
Indicates that a rescue operation is organized, directed, or managed by a particular coordinating entity.
-
D.
coordinatedUnder
Indicates that one entity is organized, directed, or managed under the authority or coordination of another entity.
-
E.
coordina
Indicates that one entity organizes, directs, or harmonizes the actions or efforts of another entity or group toward a common goal.
- 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_69ee9cfe16088190a3dddd68e3c7b1ea |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f615adea108190900f6809d6cdeb81 |
completed | May 2, 2026, 3:18 p.m. |
| PD | Predicate disambiguation | batch_69f60b8bb0d08190ab5a9a2a8847c6f4 |
completed | May 2, 2026, 2:34 p.m. |
| PDg | Predicate description generation | batch_69f60f24ed608190bffe6c6084fc2f7a |
completed | May 2, 2026, 2:50 p.m. |
Created at: April 27, 2026, 2:19 a.m.