Triple
T21854740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2 Broke Girls |
E539593
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Max Black |
—
|
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: Max Black | Statement: [2 Broke Girls, mainCharacter, Max Black]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Max Black Context triple: [2 Broke Girls, mainCharacter, Max Black]
-
A.
Max Black
chosen
Max Black is a sarcastic, street-smart Brooklyn waitress and aspiring cupcake entrepreneur who co-leads the sitcom "2 Broke Girls."
-
B.
Max Black
Max Black was a 20th-century analytic philosopher known for his influential work in the philosophy of language, logic, and metaphysics.
-
C.
Ben Black
Ben Black is a member of the prominent Black family, known primarily as the son of billionaire investor and Apollo Global Management co-founder Leon Black.
-
D.
Matt Black
Matt Black is a British DJ, producer, and co-founder of the influential electronic music duo Coldcut and the independent record label Ninja Tune.
-
E.
Matt Black
Matt Black is an American documentary photographer renowned for his stark black-and-white work on poverty, migration, and environmental issues, particularly in rural and marginalized communities.
- 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_69e0c47829648190bbe2d1d7033768ec |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0bd5ba9288190af962117124f6483 |
completed | April 28, 2026, 1:59 p.m. |
Created at: April 16, 2026, 6:56 p.m.