Triple
T34782304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sabotage (2014 film) |
E1002701
|
entity |
| Predicate | leadStudioMarketedStar |
P181890
|
FINISHED |
| Object | Arnold Schwarzenegger |
E17440
|
NE 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: Arnold Schwarzenegger | Statement: [Sabotage (2014 film), leadStudioMarketedStar, Arnold Schwarzenegger]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leadStudioMarketedStar Context triple: [Sabotage (2014 film), leadStudioMarketedStar, Arnold Schwarzenegger]
-
A.
leadStudioStar
Indicates that a person is the primary or top-billed star in a studio’s production.
-
B.
leadStudioSystem
Indicates that a studio system serves as the primary producer or overseeing entity for a particular work or project.
-
C.
leadStudioHead
Indicates that one entity serves as the primary or head studio leader responsible for another entity (such as a project, production, or organization).
-
D.
ownedStudio
Indicates that one entity possessed ownership or controlling interest in a particular studio.
-
E.
marketedWith
Indicates that two or more products or services are promoted together as part of the same marketing effort or campaign.
- F. None of above. chosen
Provenance (5 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_69f76db47d408190a24fc7164439ea2d |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f782f4f10081908f97f6d0d2dbeec7 |
completed | May 3, 2026, 5:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3779404eec819080465df1b3fdd4dc |
completed | June 21, 2026, 5:40 a.m. |
| PD | Predicate disambiguation | batch_69f780ff71cc8190a67e71076fbad81a |
completed | May 3, 2026, 5:08 p.m. |
| PDg | Predicate description generation | batch_69f782f416c081908bdd9b1ad456f0e2 |
completed | May 3, 2026, 5:16 p.m. |
Created at: May 3, 2026, 3:59 p.m.