Triple
T29579053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anthony Quinn as Quasimodo |
E753522
|
entity |
| Predicate | characterEmotionTrait |
P87208
|
FINISHED |
| Object | tormented |
—
|
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: tormented | Statement: [Anthony Quinn as Quasimodo, characterEmotionTrait, tormented]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterEmotionTrait Context triple: [Anthony Quinn as Quasimodo, characterEmotionTrait, tormented]
-
A.
emotionalTrait
chosen
Indicates that an entity possesses a particular emotional characteristic, disposition, or affective quality.
-
B.
associatedCharacterTrait
Indicates a relationship where a character is linked to, or described by, a particular trait or quality.
-
C.
emotionPersonified
Indicates that an abstract emotion is represented or depicted as if it were a person or human-like agent.
-
D.
hasPersonalityDescribedAs
Indicates that an entity possesses a personality characterized or labeled in a particular way.
-
E.
secondaryCharacterTrait
Indicates that a secondary or supporting character possesses a particular attribute, quality, or personality trait.
- 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_69f0ef80bf8c8190ad286e99f7df0c63 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69fd76d1e5208190a6f26651492d1e3c |
completed | May 8, 2026, 5:38 a.m. |
| PD | Predicate disambiguation | batch_69fd702a226c81908edfda00f4be4130 |
completed | May 8, 2026, 5:10 a.m. |
Created at: April 28, 2026, 6:05 p.m.