Triple
T38127176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minamoto-shi |
E952108
|
entity |
| Predicate | traditionalEnemyColor |
P112560
|
FINISHED |
| Object | red banners of the Taira clan |
—
|
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: red banners of the Taira clan | Statement: [Minamoto-shi, traditionalEnemyColor, red banners of the Taira clan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalEnemyColor Context triple: [Minamoto-shi, traditionalEnemyColor, red banners of the Taira clan]
-
A.
opposedColorsOfRivals
chosen
Indicates that the entities are rivals whose associated colors are in opposition to each other.
-
B.
traditionalKitColor
Indicates the customary or historically established color scheme used for an entity’s standard or primary kit or uniform.
-
C.
castleColor
Indicates that a castle has a specific color.
-
D.
primaryEnemy
Indicates that one entity is the main or most significant adversary or opponent of another entity.
-
E.
traditionalOpponents
Indicates that two entities customarily or historically compete or conflict with each other as recognized rivals or adversaries.
- 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_69f76f083548819082bd2bbf53c79e8e |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fff59a00a881909b35b799654b3c45 |
completed | May 10, 2026, 3:03 a.m. |
| PD | Predicate disambiguation | batch_69fff4d0a2e081909c972189b33d0128 |
completed | May 10, 2026, 3 a.m. |
Created at: May 3, 2026, 4:21 p.m.