Triple
T12646902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crosby Theatre |
E302048
|
entity |
| Predicate | dedicatedTo |
P500
|
FINISHED |
| Object | John Crosby |
E290823
|
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: John Crosby | Statement: [Crosby Theatre, dedicatedTo, John Crosby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Crosby Context triple: [Crosby Theatre, dedicatedTo, John Crosby]
-
A.
John Crosby
chosen
John Crosby was an American conductor and arts administrator best known as the founding director and long-time leader of the Santa Fe Opera.
-
B.
William Crosby Dawson
William Crosby Dawson was a 19th-century American politician and lawyer from Georgia who served in the U.S. Congress and the U.S. Senate.
-
C.
John Grove
John Grove is a publisher associated with the work "The Witty Fair One."
-
D.
John Brock
John Brock is a relatively obscure individual whose name is shared with several more widely known figures across fields such as politics, sports, and academia.
-
E.
John Shelby
John Shelby is a key member of the Shelby crime family in the British television series "Peaky Blinders," known for his fierce loyalty, volatility, and role in the gang's violent operations.
- 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_69d7bdec9f9c8190b4bac675b7588211 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9614cefdc81908cfc4a4d04aa6eda |
completed | April 10, 2026, 8:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6687bbb408190b80da2d0310f82c5 |
completed | May 2, 2026, 9:11 p.m. |
Created at: April 9, 2026, 5:17 p.m.