Triple
T35014427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Judas Contract |
E1010014
|
entity |
| Predicate | traitorCharacter |
P139892
|
FINISHED |
| Object | Terra |
E1001827
|
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: Terra | Statement: [The Judas Contract, traitorCharacter, Terra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traitorCharacter Context triple: [The Judas Contract, traitorCharacter, Terra]
-
A.
leadAntagonistCharacter
Indicates that one character serves as the primary opposing or villainous force in relation to another entity in the narrative.
-
B.
antagonistAlterEgoOf
Indicates that one entity serves as the primary opposing force or enemy of another entity’s alternate identity or secret persona.
-
C.
notableTurncoat
chosen
Indicates that an entity is recognized for having betrayed or switched allegiance from one side, group, or cause to another.
-
D.
protagonistAllegiance
Indicates the group, cause, or side with which the main character is aligned or to which they show loyalty.
-
E.
plotCharacter
Indicates a relationship where a character plays a role or participates in the narrative plot of a story or work.
- 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_69f76dcc3ac8819096a3ed52f5fa2523 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7858aa5508190a07dde993b3356fc |
completed | May 3, 2026, 5:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37d93d6ae8819083158efbf899eb0c |
completed | June 21, 2026, 12:29 p.m. |
| PD | Predicate disambiguation | batch_69f7841812f081909d878955d114088e |
completed | May 3, 2026, 5:21 p.m. |
Created at: May 3, 2026, 4:01 p.m.