Triple
T31953356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Team Captain America |
E815839
|
entity |
| Predicate | includesFormerBrainwashedAssassin |
P138555
|
FINISHED |
| Object | Bucky Barnes |
E58707
|
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: Bucky Barnes | Statement: [Team Captain America, includesFormerBrainwashedAssassin, Bucky Barnes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesFormerBrainwashedAssassin Context triple: [Team Captain America, includesFormerBrainwashedAssassin, Bucky Barnes]
-
A.
underwentBrainwashingBy
Indicates that one entity was subjected to brainwashing carried out by another entity.
-
B.
hasAssassinCharacter
chosen
Indicates that an entity includes, features, or is associated with a character whose role or function is that of an assassin.
-
C.
hasKillerProtagonist
Indicates that the main character in a work is a killer or has committed killing as a defining aspect of their role.
-
D.
hasAmnesiacProtagonist
Indicates that the work features a main character who suffers from significant memory loss, which is central to the story or their role.
-
E.
hasKiller
Indicates that one entity is the killer or cause of death of another entity.
- F. None of above.
Provenance (4 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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a01a18e350481909f848686568d19bc |
completed | May 11, 2026, 9:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2f010c5e608190b21b23f761968458 |
completed | June 14, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_6a01a121b67c81908a6c5be9eb8e9ca5 |
completed | May 11, 2026, 9:28 a.m. |
Created at: May 1, 2026, 12:08 a.m.