Triple
T13921671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blythe Danner |
E334759
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Huff |
E409596
|
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: Huff | Statement: [Blythe Danner, notableWork, Huff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Huff Context triple: [Blythe Danner, notableWork, Huff]
-
A.
Huff
Huff is a surname most prominently associated with Sam Huff, a Hall of Fame American football linebacker who starred for the New York Giants and Washington in the NFL.
-
B.
Huff
chosen
Huff is an American television dramedy series that follows a psychiatrist whose life unravels after a patient’s suicide, featuring Oliver Platt in a prominent supporting role.
-
C.
Huff-Duff
Huff-Duff (high-frequency direction finding) was a World War II radio direction-finding technology used primarily by the Allies to locate enemy submarines and ships by tracking their radio transmissions.
-
D.
Humph
Humph is a shortened, informal given name typically derived from Humphrey.
-
E.
Puthuff
Puthuff is a surname most notably associated with American landscape painter Hanson Puthuff.
- 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_69d81c5f739081908bc05b2461f54828 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2aa5c1f481908a9d8786872f08fe |
completed | April 14, 2026, 11:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7ce7c4a788190a1e7619a00ab0c2e |
completed | May 3, 2026, 10:38 p.m. |
Created at: April 9, 2026, 10:16 p.m.