Triple
T30250482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perponcher’s Division |
E769185
|
entity |
| Predicate | roleAtQuatreBras |
P28183
|
FINISHED |
| Object | holding the crossroads against French attacks |
—
|
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: holding the crossroads against French attacks | Statement: [Perponcher’s Division, roleAtQuatreBras, holding the crossroads against French attacks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleAtQuatreBras Context triple: [Perponcher’s Division, roleAtQuatreBras, holding the crossroads against French attacks]
-
A.
roleInBattleOfGravelotte
Indicates the specific role or participation an entity had in the Battle of Gravelotte.
-
B.
roleAtWaterloo
Indicates the specific position, function, or capacity an entity held in relation to the Battle of Waterloo.
-
C.
roleInGallicWars
Indicates the role or involvement an entity had in the events or campaigns of the Gallic Wars.
-
D.
roleAtAntietam
Indicates the specific role, position, or function an entity held during the Battle of Antietam.
-
E.
notableBattleRole
chosen
Indicates the specific role or function an entity played in a notable or historically significant battle.
- 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_69f224831dc08190b2e569b987264057 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6abaa1f648190b77073771df3bf3b |
completed | May 3, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1e84b88190b025f6ca40f17a8a |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 29, 2026, 7:40 p.m.