Triple
T33570832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jessica Chastain as Sara |
E859893
|
entity |
| Predicate | sharesScreenWithActor |
P134423
|
FINISHED |
| Object | Chris Hemsworth |
—
|
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: Chris Hemsworth | Statement: [Jessica Chastain as Sara, sharesScreenWithActor, Chris Hemsworth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesScreenWithActor Context triple: [Jessica Chastain as Sara, sharesScreenWithActor, Chris Hemsworth]
-
A.
sharesScreenWithCharacter
chosen
Indicates that one character appears on screen at the same time as another character, sharing the visual scene.
-
B.
sharesActorWith
Indicates that two entities are associated with at least one of the same actors (e.g., performers or participants) in common.
-
C.
sharesStageWith
Indicates that two or more performers appear or perform together on the same stage during a shared event or production.
-
D.
sharedSceneWith
Indicates that two entities appear together within the same scene or setting.
-
E.
sharesControlWith
Indicates that control, authority, or decision-making power over something is jointly held or exercised between the related entities.
- 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_69f3497c1d288190a844ea699914e038 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ffb1218cb08190a814c7f0833501a7 |
completed | May 9, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69ffb083d6988190b2757e0cfd629b75 |
completed | May 9, 2026, 10:09 p.m. |
Created at: May 1, 2026, 1:40 a.m.