Triple
T2523961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arnie Grape |
E55990
|
entity |
| Predicate | plotRole |
P17462
|
FINISHED |
| Object | central family member in What's Eating Gilbert Grape |
—
|
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: central family member in What's Eating Gilbert Grape | Statement: [Arnie Grape, plotRole, central family member in What's Eating Gilbert Grape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plotRole Context triple: [Arnie Grape, plotRole, central family member in What's Eating Gilbert Grape]
-
A.
plotInvolvement
chosen
Indicates that an entity participates in, contributes to, or is affected by the events or storyline of a narrative work.
-
B.
depictsPersonRole
Indicates that an image or representation shows a person in a specific role, function, or capacity.
-
C.
actingRoleType
Indicates the specific type or category of role an entity performs when acting in a particular capacity or function.
-
D.
displayRole
Indicates the role or position an entity holds in the context of how it is presented or shown in a display.
-
E.
plannedRole
Indicates that an entity is expected or intended to assume a particular role or function in a planned or future context.
- 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_69ab4a48e4f081908f1218d244608659 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd252f1c88190ac93604542f80f49 |
completed | March 7, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69abd0c144b0819092f32a13c1d127e5 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:46 p.m.