Triple
T2236672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Sahagún |
E49296
|
entity |
| Predicate | strengthFrenchCavalry |
P36039
|
FINISHED |
| Object | approximately 600–700 troopers |
—
|
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: approximately 600–700 troopers | Statement: [Battle of Sahagún, strengthFrenchCavalry, approximately 600–700 troopers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: strengthFrenchCavalry Context triple: [Battle of Sahagún, strengthFrenchCavalry, approximately 600–700 troopers]
-
A.
commandingForce2Strength
chosen
Indicates that a commanding force possesses or exerts a particular level or measure of strength.
-
B.
typeOfTroops
Indicates the specific category or kind of military forces involved in or associated with an entity or event.
-
C.
FrenchCommander
Indicates that an entity serves as a military commander associated with France.
-
D.
besiegingForce
Indicates a military group that is surrounding and attacking a target location or force in an attempt to capture or subdue it.
-
E.
commandingForce1Strength
Indicates that one entity has a certain level or measure of strength in its role as the primary commanding force over another entity or situation.
- 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_69a88aa84bdc819086df50e9c20b301e |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc09573848190bf91eddcc2fa0061 |
completed | March 7, 2026, 6:07 a.m. |
| PD | Predicate disambiguation | batch_69abbdafc07881909101266a33ae7031 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.