Triple
T17977806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rachel Bloom |
E449520
|
entity |
| Predicate | characterPortrayed |
P1507
|
FINISHED |
| Object | Rebecca Bunch |
—
|
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: Rebecca Bunch | Statement: [Rachel Bloom, characterPortrayed, Rebecca Bunch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rebecca Bunch Context triple: [Rachel Bloom, characterPortrayed, Rebecca Bunch]
-
A.
Rebecca Bunch
chosen
Rebecca Bunch is the neurotic, impulsive, and romantically fixated lawyer who serves as the protagonist of the musical comedy-drama series "Crazy Ex-Girlfriend."
-
B.
Rebecca Sylvester
Rebecca Sylvester is a musician featured as a track artist on the album "Camoufleur."
-
C.
Rebecca Ranson
Rebecca Ranson was an American playwright and activist known for her pioneering work in LGBTQ+ theater and advocacy during the AIDS crisis.
-
D.
Rebecca Trotman
Rebecca Trotman is a film editor known for her work on the movie "Twice Upon a Time."
-
E.
Rebecca Huntley
Rebecca Huntley is a film producer best known for her work on the animated feature "The Bad Guys."
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b200e9108190bcdde5ba7938ba94 |
completed | April 19, 2026, 10:44 a.m. |
Created at: April 10, 2026, 10:22 a.m.