Triple
T37810092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terror in the Aisles |
E942616
|
entity |
| Predicate | compilesScenesFrom |
P110949
|
FINISHED |
| Object | horror films |
—
|
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: horror films | Statement: [Terror in the Aisles, compilesScenesFrom, horror films]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compilesScenesFrom Context triple: [Terror in the Aisles, compilesScenesFrom, horror films]
-
A.
featuresSceneFrom
chosen
Indicates that one entity (such as a work or media item) includes or presents a particular scene taken from another entity.
-
B.
numberOfScenes
Indicates the total count of distinct scenes associated with or contained within an entity.
-
C.
scenes
Indicates that one entity is a scene or setting in which the other entity occurs, appears, or is depicted.
-
D.
remainingScenesCompletedUsing
Indicates that the completion of the remaining scenes is achieved through or by means of the specified method, resource, or process.
-
E.
scoredScenes
Indicates that one entity has composed or provided a musical score for specific scenes associated with another entity.
- 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_69f76ee8104c8190ab17133ccd8f86e6 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbb9e8108c8190ae1c7940b1677e95 |
completed | May 6, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fbb141605c8190b9c27d70352522db |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:19 p.m.