Triple
T4761311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krampus (2015 film) |
E105703
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | David Koechner |
E372916
|
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: David Koechner | Statement: [Krampus (2015 film), starring, David Koechner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Koechner Context triple: [Krampus (2015 film), starring, David Koechner]
-
A.
David Koechner
chosen
David Koechner is an American character actor and comedian best known for his scene-stealing roles in films like Anchorman and the TV series The Office.
-
B.
Rob Riggle
Rob Riggle is an American actor, comedian, and former Marine officer known for his energetic, often over-the-top roles in film and television comedies.
-
C.
Will Murray
Will Murray is an American writer best known for his extensive work continuing classic pulp fiction series, particularly the Doc Savage novels.
-
D.
Paul F. Tompkins
Paul F. Tompkins is an American comedian, actor, and writer known for his stand-up, podcast appearances, and character roles in television and film.
-
E.
Rob Schneider
Rob Schneider is an American actor and comedian known for his roles in numerous Adam Sandler films and other broad Hollywood comedies.
- 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_69bd43f14cac819081c7c69803648211 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd650eefe08190b99f9f01b121dbfd |
completed | March 20, 2026, 3:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be67c17eac8190bde930228a0f599a |
completed | March 21, 2026, 9:41 a.m. |
Created at: March 20, 2026, 1:20 p.m.