Triple
T3939166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2020 New Hampshire gubernatorial election |
E91989
|
entity |
| Predicate | losingCandidate |
P354
|
FINISHED |
| Object | Dan Feltes |
E399943
|
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: Dan Feltes | Statement: [2020 New Hampshire gubernatorial election, losingCandidate, Dan Feltes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dan Feltes Context triple: [2020 New Hampshire gubernatorial election, losingCandidate, Dan Feltes]
-
A.
Dan Feltes
chosen
Dan Feltes is an American lawyer and Democratic politician who served in the New Hampshire State Senate and ran for governor of New Hampshire in 2020.
-
B.
Robert Hohman
Robert Hohman is an American entrepreneur best known as the co-founder and former CEO of Glassdoor, a popular platform for anonymous employee reviews and salary information.
-
C.
Dan Foos
Dan Foos is a writer best known as the creator of the story for the film "Red Eye."
-
D.
Bill Elfers
Bill Elfers was an American venture capitalist best known for co-founding the influential Silicon Valley and Boston-based firm Greylock Partners.
-
E.
Fred Schuler
Fred Schuler is a cinematographer best known for his work on films such as the 1980 comedy "Stir Crazy."
- 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_69aed965502c8190904ebad1203a4ae8 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeedfb12b88190a6ca6574b1aadb6e |
completed | March 9, 2026, 3:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b556173f848190bf8b879a7c61a43f |
completed | March 14, 2026, 12:35 p.m. |
Created at: March 9, 2026, 3:24 p.m.