Triple
T11292991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Christian |
E267374
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Dave Christian |
E225120
|
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: Dave Christian | Statement: [Roger Christian, relative, Dave Christian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dave Christian Context triple: [Roger Christian, relative, Dave Christian]
-
A.
Dave Christian
chosen
Dave Christian is an American former professional ice hockey forward best known as a member of the "Miracle on Ice" 1980 U.S. Olympic team who went on to have a long NHL career.
-
B.
David Martin
David Martin is a film editor best known for his work on the 1986 biographical drama "Sid and Nancy."
-
C.
Scott Heiferman
Scott Heiferman is an American entrepreneur best known for co-founding the social networking platform Meetup, which helps people organize and attend local in-person events.
-
D.
Dan Talbot
Dan Talbot was an influential American film distributor and exhibitor known for championing foreign and independent cinema in the United States.
-
E.
Christopher B. Duncan
Christopher B. Duncan is an American actor best known for his comedic television roles, including portrayals of presidential and authority figures.
- 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_69d6aac993a08190a6f36445ebaf9a43 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e98b149481909f432a6b9ef8bfbb |
completed | April 9, 2026, 6:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4f4a57d6881909a1e65744111ad8b |
completed | April 19, 2026, 3:28 p.m. |
Created at: April 8, 2026, 9:32 p.m.