Triple
T9902988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarbanes |
E182331
|
entity |
| Predicate | usedBy |
P260
|
FINISHED |
| Object | John Sarbanes |
E185542
|
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 Sarbanes | Statement: [Sarbanes, usedBy, John Sarbanes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Sarbanes Context triple: [Sarbanes, usedBy, John Sarbanes]
-
A.
John Sarbanes
chosen
John Sarbanes is an American politician and attorney who has served as a Democratic U.S. Representative from Maryland.
-
B.
Paul Sarbanes
Paul Sarbanes was a long-serving U.S. Senator from Maryland best known for co-authoring major corporate governance reforms in the early 2000s.
-
C.
Tom Reid
Tom Reid is the brother of American actress Tara Reid, known for her roles in films like "American Pie" and "The Big Lebowski."
-
D.
Tom Harkin
Tom Harkin is an American Democratic politician and longtime U.S. senator from Iowa known for his leadership on disability rights and authorship of the Americans with Disabilities Act.
-
E.
Joe Lieberman
Joe Lieberman was a longtime U.S. senator from Connecticut known for his centrist politics and role as Al Gore’s vice-presidential running mate in the 2000 election.
- 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_69ca82876f8081909cf75df0f99bb13f |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb4e391888190a3f5e5a1bf1cf9ff |
completed | April 2, 2026, 12:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2289a547481909997f8f2dcb5e84c |
completed | April 5, 2026, 9:17 a.m. |
Created at: March 30, 2026, 8:40 p.m.