Triple
T9253864
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jacob King |
E222390
|
entity |
| Predicate | appearsAlongsideCharacter |
P25756
|
FINISHED |
| Object | Bianca King |
E786303
|
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: Bianca King | Statement: [Jacob King, appearsAlongsideCharacter, Bianca King]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bianca King Context triple: [Jacob King, appearsAlongsideCharacter, Bianca King]
-
A.
Bianca King
chosen
Bianca King is a Filipino actress and model known for her roles in Philippine television dramas and films.
-
B.
Bianca Taylor
Bianca Taylor is a character in the "Creed" film series, known as Adonis Creed's love interest and a talented musician coping with progressive hearing loss.
-
C.
Nicole King
Nicole King is a film producer known for her work on the family comedy movie "Yes Day."
-
D.
Jessica King
Jessica King is a character in the supernatural thriller film "The Gift," involved in the mysterious events surrounding a small-town community.
-
E.
Katie King
Katie King is the daughter of British television presenter and former "Countdown" co-host Carol Vorderman.
- 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_69ca841e4cd481908e738c74e958eaea |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd06b1f6bc81908115e22652d0c85e |
completed | April 1, 2026, 11:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d09bde36688190bf66669f585dcee7 |
completed | April 4, 2026, 5:04 a.m. |
Created at: March 30, 2026, 7:31 p.m.