Triple
T38049309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danny Deever |
E949708
|
entity |
| Predicate | characterRoleOfDannyDeever |
P192169
|
FINISHED |
| Object | condemned soldier |
—
|
LITERAL 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: condemned soldier | Statement: [Danny Deever, characterRoleOfDannyDeever, condemned soldier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterRoleOfDannyDeever Context triple: [Danny Deever, characterRoleOfDannyDeever, condemned soldier]
-
A.
leadActorForCharacterDanny
Indicates that a person is the primary actor portraying the character named Danny in a production.
-
B.
characterPlayedByDanDuryea
Indicates that the referenced character is portrayed or played by the actor Dan Duryea.
-
C.
describesCharacterRole
chosen
Indicates that one entity specifies or defines the narrative or functional role played by another entity.
-
D.
characterPlayedByDeanJones
Indicates that a given character is portrayed or acted by Dean Jones.
-
E.
characterPortrayedByRobertDuvall
Indicates that the character is portrayed by the actor Robert Duvall.
- F. None of above.
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_69f76f000cf081908c11fb5443b392e6 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a000be59ad88190a6aa3a42c097796d |
completed | May 10, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_6a000ab6e9bc81908300b81d004e5921 |
completed | May 10, 2026, 4:33 a.m. |
Created at: May 3, 2026, 4:20 p.m.