Triple
T2854311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Batman Returns |
E63163
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Selina Kyle |
E135917
|
NE 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: Selina Kyle | Statement: [Batman Returns, mainCharacter, Selina Kyle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Selina Kyle Context triple: [Batman Returns, mainCharacter, Selina Kyle]
-
A.
Selina Kyle
chosen
Selina Kyle is a cunning and morally ambiguous cat burglar in the Batman universe, best known by her alter ego Catwoman.
-
B.
Selina
Selina is a feminine given name of Latin origin, commonly used in English-speaking countries.
-
C.
Kate Bishop
Kate Bishop is a young, skilled archer and protégé of Clint Barton in the Marvel universe who takes up the Hawkeye mantle.
-
D.
Harley Quinn
Harley Quinn is a chaotic, acrobatic antiheroine from DC Comics known for her clown-themed appearance, unpredictable behavior, and complex relationship with the Joker.
-
E.
Amanda Reed
Amanda Reed was the benefactor whose bequest and vision led to the establishment of Reed College in Portland, Oregon.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ab4c407c408190857d25e027155ce9 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf5f21348190a574fa86bc71c76f |
completed | March 7, 2026, 8:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b01d8774cc8190aa6ed40b26c4a568 |
completed | March 10, 2026, 1:32 p.m. |
Created at: March 6, 2026, 10:02 p.m.