Triple
T10657130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Wisner |
E251120
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Wisner |
E150848
|
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: Wisner | Statement: [Frank Wisner, familyName, Wisner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wisner Context triple: [Frank Wisner, familyName, Wisner]
-
A.
Wisner
chosen
Wisner is a surname of German origin borne by various notable individuals across politics, intelligence, and other fields.
-
B.
Wisser
The Wisser is a river in Germany that serves as a right-bank tributary of the Sieg.
-
C.
Weissman
Weissman is a surname most prominently associated with Drew Weissman, the Nobel Prize–winning physician-scientist whose work on mRNA technology enabled the development of COVID-19 vaccines.
-
D.
Whitmire
Whitmire is a given name associated with David Whitmire Hearst, a member of the Hearst family.
-
E.
Woolsey
Woolsey is a surname most notably associated with Theodore Dwight Woolsey, a prominent 19th-century American academic and president of Yale College.
- 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_69d6aa5a4c4881908f39be6efe5981e5 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6e0157dbc81909ef7d61f65b2fd93 |
completed | April 8, 2026, 11:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98857ec248190bb655d36981a000a |
completed | April 10, 2026, 11:31 p.m. |
Created at: April 8, 2026, 9:07 p.m.