Triple
T8213604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Betsy Gotbaum |
E191880
|
entity |
| Predicate | predecessor |
P97
|
FINISHED |
| Object | Mark Green |
E191879
|
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: Mark Green | Statement: [Betsy Gotbaum, predecessor, Mark Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Green Context triple: [Betsy Gotbaum, predecessor, Mark Green]
-
A.
Mark Green
chosen
Mark Green is an American lawyer, author, and progressive politician who became prominent as New York City's first elected Public Advocate and a frequent critic of corporate and governmental abuses.
-
B.
Mike Sullivan
Mike Sullivan is an American professional ice hockey coach best known for leading the Pittsburgh Penguins to multiple Stanley Cup championships.
-
C.
Max Cullen
Max Cullen is an Australian character actor known for his extensive work in film, television, and theatre over several decades.
-
D.
Mike Conlon
Mike Conlon is a central character in the action-thriller film "Run All Night," depicted as the estranged son of a hitman who becomes entangled in a violent criminal conflict.
-
E.
Mike Wilson
Mike Wilson is known as the father of former child actress and writer Mara Wilson.
- 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_69ca82c8c054819087fedd9a5436b8a3 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb76e1ffa081908883338e7d3a7c6d |
completed | March 31, 2026, 7:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccedea881481909f9348778290eb63 |
completed | April 1, 2026, 10:05 a.m. |
Created at: March 30, 2026, 5:44 p.m.