Triple
T5108360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Bemis Heights |
E115153
|
entity |
| Predicate | forceStrengthBritish |
P40540
|
FINISHED |
| Object | approximately 6,000–7,000 troops |
—
|
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 6,000–7,000 troops | Statement: [Battle of Bemis Heights, forceStrengthBritish, approximately 6,000–7,000 troops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: forceStrengthBritish Context triple: [Battle of Bemis Heights, forceStrengthBritish, approximately 6,000–7,000 troops]
-
A.
strength_British_side
Indicates the level or measure of military or strategic power possessed by the British side in a given context.
-
B.
strengthBritishForces
chosen
Indicates the numerical size or combat capacity of British military forces in a given context or operation.
-
C.
fleetStrengthEnglish
Indicates the relative military or naval power level associated with a fleet, expressed or categorized in English terms.
-
D.
BritishForcesType
Indicates that an entity is classified as a type or category within the British armed forces.
-
E.
commandingForce2Strength
Indicates that a commanding force possesses or exerts a particular level or measure of strength.
- 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_69bd4440b3348190be1251fd8b7951f1 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75aa6b088190b02cdb66ec4a11f0 |
completed | March 20, 2026, 4:28 p.m. |
| PD | Predicate disambiguation | batch_69bd715fe3a8819087d3065adddba515 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:41 p.m.