Triple
T37137607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Accused (US TV series) |
E920011
|
entity |
| Predicate | hasOpeningSceneType |
P17856
|
FINISHED |
| Object | courtroom entry of defendant |
—
|
LITERAL 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: courtroom entry of defendant | Statement: [Accused (US TV series), hasOpeningSceneType, courtroom entry of defendant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOpeningSceneType Context triple: [Accused (US TV series), hasOpeningSceneType, courtroom entry of defendant]
-
A.
hasOpeningScene
Indicates that a work (such as a film, show, or story) possesses a specific initial scene that begins or introduces its narrative.
-
B.
hasOpeningSceneArgumentAbout
Indicates that the opening scene of a work features an argument involving the specified entities.
-
C.
hasOpeningFeature
Indicates that an entity possesses a specific characteristic, element, or attribute related to its opening or entry point.
-
D.
hasOpeningCreditsUsage
Indicates that something is used or appears specifically in the opening credits of a work.
-
E.
hasOpeningType
chosen
Indicates that one entity has, features, or is characterized by a particular type or kind of opening.
- 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_69f76e9e9d008190a250b0387c992c74 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd44474ed48190ac372e4c88d762ed |
completed | May 8, 2026, 2:02 a.m. |
| PD | Predicate disambiguation | batch_69fd41ef28a48190a66959be5c964461 |
completed | May 8, 2026, 1:52 a.m. |
Created at: May 3, 2026, 4:15 p.m.