Triple
T22021453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gilda Dent |
E543854
|
entity |
| Predicate | romanticRelationshipWith |
P9994
|
FINISHED |
| Object | Harvey Dent |
—
|
NE NERFINISHED |
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: Harvey Dent | Statement: [Gilda Dent, romanticRelationshipWith, Harvey Dent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harvey Dent Context triple: [Gilda Dent, romanticRelationshipWith, Harvey Dent]
-
A.
Harvey Dent
chosen
Harvey Dent is a prominent Gotham City district attorney who becomes the tragic, disfigured villain Two-Face in the Batman universe.
-
B.
Rich Gotham
Rich Gotham is an American sports executive best known for serving as the president of the NBA’s Boston Celtics.
-
C.
Hardy Justice
Hardy Justice is a film producer best known for his work on the period drama "Stage Beauty."
-
D.
James Gordon
James Gordon is Gotham City's principled police commissioner and a key ally of Batman in the fight against crime and corruption.
-
E.
James Gordon
James Gordon is a senior executive and key decision-maker at Clearlake Capital, a prominent private equity and investment firm.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127c7b3308190ac056bef6f82722e |
completed | April 28, 2026, 9:33 p.m. |
Created at: April 16, 2026, 8:23 p.m.