Triple
T6700936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Castillon |
E152875
|
entity |
| Predicate | EnglishForceCharacteristic |
P39522
|
FINISHED |
| Object | relief army led by John Talbot |
—
|
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: relief army led by John Talbot | Statement: [Battle of Castillon, EnglishForceCharacteristic, relief army led by John Talbot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: EnglishForceCharacteristic Context triple: [Battle of Castillon, EnglishForceCharacteristic, relief army led by John Talbot]
-
A.
EnglishCommander
chosen
Indicates that one entity serves as a military commander or leader for English forces in relation to another entity.
-
B.
EnglishVersionFeature
Indicates that the related item is a feature or aspect specifically associated with the English-language version of something.
-
C.
EnglishRole
Indicates that one entity serves a particular role or function within the context of the English language for another entity.
-
D.
usesFormCharacteristic
Indicates that one entity employs or relies on a particular formal property or structural characteristic of another entity in performing an action or fulfilling a function.
-
E.
englishFlagship
Indicates that an entity participates in or is associated with an English flagship program (typically an intensive, advanced English language or studies track).
- 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_69c68807adbc8190b8632df42b39eda0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d16897e48190b43eda2206b14d6a |
completed | March 27, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_69c6d089c7488190a00853fb12f53b2a |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:05 p.m.