Triple
T8343679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Warner |
E195982
|
entity |
| Predicate | precededBy |
P97
|
FINISHED |
| Object | John Warner |
E67768
|
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 Warner | Statement: [Mark Warner, precededBy, John Warner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Warner Context triple: [Mark Warner, precededBy, John Warner]
-
A.
John Warner
chosen
John Warner was a long-serving U.S. Senator from Virginia and former Secretary of the Navy known for his influential role in national defense and bipartisan politics.
-
B.
Jim Webb
Jim Webb is an American politician, author, and former U.S. Senator from Virginia who also served as Secretary of the Navy and is known for his military service in the Vietnam War.
-
C.
George Herbert Allen
George Herbert Allen is an American politician and attorney who served as Governor of Virginia and later as a United States Senator.
-
D.
George Herbert Allen
George Herbert Allen was the father of American football coach and NFL Hall of Famer George Allen.
-
E.
Warren Rudman
Warren Rudman was a U.S. Senator from New Hampshire known for his fiscal conservatism and co-sponsorship of landmark federal budget deficit reduction legislation.
- 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_69ca82edd63c8190b876b8465464c5fa |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7febde288190bf4677fb24d26b83 |
completed | March 31, 2026, 8:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc733f7848190ab60098cb178dbfc |
completed | April 2, 2026, 1:32 a.m. |
Created at: March 30, 2026, 5:58 p.m.