Triple
T20817799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | axe (1980 film) |
E512486
|
entity |
| Predicate | actionInScene |
P139828
|
FINISHED |
| Object | used to chop through bathroom door |
—
|
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: used to chop through bathroom door | Statement: [axe (1980 film), actionInScene, used to chop through bathroom door]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: actionInScene Context triple: [axe (1980 film), actionInScene, used to chop through bathroom door]
-
A.
performedInScene
chosen
Indicates that an action or event took place within a specific scene or setting.
-
B.
frameOfAction
Indicates the contextual situation, setting, or circumstances within which an action or event takes place.
-
C.
liveAction
Indicates that an entity is a live-action (non-animated) adaptation, portrayal, or version of another entity.
-
D.
actsOn
Indicates that one entity performs an action that affects, targets, or is directed toward another entity.
-
E.
protagonistAction
Indicates that the referenced entity performs the central or primary action associated with the main character in a narrative or scenario.
- 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_69e0b4cd25088190b48ca9700cd24efc |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2f429388190809dd532278fe310 |
completed | April 21, 2026, 12:21 a.m. |
| PD | Predicate disambiguation | batch_69e5c99ca55481908e8d434fa901cfd6 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:41 p.m.