Triple
T23212118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barbara Gordon |
E580623
|
entity |
| Predicate | allyOf |
P4662
|
FINISHED |
| Object | Black Canary |
—
|
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: Black Canary | Statement: [Barbara Gordon, allyOf, Black Canary]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Black Canary Context triple: [Barbara Gordon, allyOf, Black Canary]
-
A.
Black Canary
chosen
Black Canary is a DC Comics superheroine known for her expert martial arts skills and her powerful ultrasonic "canary cry" sonic scream.
-
B.
Cordelia Foxx
Cordelia Foxx is a powerful witch and eventual Supreme who leads Miss Robichaux's Academy in the television series "American Horror Story: Coven."
-
C.
Dazzler
Dazzler is a Marvel Comics superheroine and mutant pop star who converts sound into powerful light-based energy.
-
D.
Cassie Cage
Cassie Cage is a key protagonist in the Mortal Kombat series, known as the daughter of Johnny Cage and Sonya Blade who combines military training with her father's flashy fighting style.
-
E.
Melissa Dyne
Melissa Dyne is an American artist and musician best known as a member of the experimental pop duo The Blow, where she contributes to the group’s sound design and conceptual production.
- 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f191620378819096362252c3b819b6 |
completed | April 29, 2026, 5:04 a.m. |
Created at: April 17, 2026, 4:07 p.m.