Triple
T20592457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richard Bull |
E505963
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bull |
—
|
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: Bull | Statement: [Richard Bull, familyName, Bull]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bull Context triple: [Richard Bull, familyName, Bull]
-
A.
Bull
Bull was the notorious nickname of Eugene "Bull" Connor, the Birmingham, Alabama public safety commissioner whose brutal enforcement of racial segregation during the Civil Rights Movement made him a national symbol of racist oppression.
-
B.
Bull
Bull is an American legal drama television series that follows a brilliant trial consultant and his team as they analyze juries and craft courtroom strategies.
-
C.
Bull
chosen
Bull is a common English surname borne by various notable individuals across fields such as politics, sports, and the arts.
-
D.
Bull
Bull is a French-based information technology and digital services company known for its work in high-performance computing and enterprise solutions.
-
E.
Bull
Bull is the common nickname of U.S. Navy Admiral William F. "Bull" Halsey Jr., a prominent World War II naval commander in the Pacific Theater.
- 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_69e0b4ba6ae88190af871e1f9522c704 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a97d63cc8190853e052d5930470d |
completed | April 20, 2026, 10:32 p.m. |
Created at: April 16, 2026, 11:40 a.m.