Triple
T32296268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevyn Major Howard |
E825106
|
entity |
| Predicate | characterNameInFullMetalJacket |
P36851
|
FINISHED |
| Object | Rafterman |
—
|
NE NERFINISHED |
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: Rafterman | Statement: [Kevyn Major Howard, characterNameInFullMetalJacket, Rafterman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterNameInFullMetalJacket Context triple: [Kevyn Major Howard, characterNameInFullMetalJacket, Rafterman]
-
A.
characterFullName
Indicates that the predicate specifies the complete, formal name of a character.
-
B.
characterName
chosen
Indicates that an entity has a specific name used to identify its character.
-
C.
protagonistFullName
Indicates that the subject entity is the full, proper name (including given and family names) of the story’s main protagonist.
-
D.
leadActorForCharacter Lieutenant Bob Coleman
Indicates that Lieutenant Bob Coleman is the primary actor portraying a specific character in a production.
-
E.
leadActorForCharacter Sergeant Al Burkhardt
Indicates that the specified person is the primary actor portraying the character Sergeant Al Burkhardt.
- 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_69f349101b788190b4f14884dc7d1ed2 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fed6da0390819096b88ef4714b144e |
completed | May 9, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69fed53517d081909966f31707625f1a |
completed | May 9, 2026, 6:33 a.m. |
Created at: May 1, 2026, 12:44 a.m.