Triple
T1207873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proof (1991 film) |
E25929
|
entity |
| Predicate | characterDisability |
P148
|
FINISHED |
| Object | blindness |
—
|
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: blindness | Statement: [Proof (1991 film), characterDisability, blindness]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterDisability Context triple: [Proof (1991 film), characterDisability, blindness]
-
A.
causeOfDisability
Indicates that one entity is the reason or source that brings about another entity’s disability.
-
B.
disability
chosen
Indicates that an entity has a physical, mental, or sensory impairment that substantially limits one or more major life activities.
-
C.
wheelchairDivision
Indicates that an entity participates in or is associated with a competition, league, or category specifically designated for wheelchair users.
-
D.
character1
Indicates that the subject is identified as the first or primary character in a narrative or context.
-
E.
character2
Indicates that a second character entity is involved in the relationship or context defined by the predicate.
- 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_69a4942b30f08190a91c60573e16b5ef |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bdc483b481908e5bfef5d2f4fc5a |
completed | March 1, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6078088190ba0221ae3368416c |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:46 p.m.