Triple
T1761450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Cannae |
E38666
|
entity |
| Predicate | estimatedRomanForces |
P31443
|
FINISHED |
| Object | about 80,000 infantry |
—
|
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: about 80,000 infantry | Statement: [Battle of Cannae, estimatedRomanForces, about 80,000 infantry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estimatedRomanForces Context triple: [Battle of Cannae, estimatedRomanForces, about 80,000 infantry]
-
A.
underRomanRule
Indicates that one entity was politically controlled or governed by the Roman state or its authorities.
-
B.
besiegingForce
Indicates a military group that is surrounding and attacking a target location or force in an attempt to capture or subdue it.
-
C.
usesRomanNumerals
Indicates that something represents numbers or sequences using the Roman numeral system rather than standard Arabic digits.
-
D.
combatantStrength
Indicates the relative level of power, capability, or effectiveness one combatant has in a conflict or confrontation compared to others.
-
E.
RomanRepresentative
Indicates that one entity serves as an official representative or agent of the Roman state, authority, or interests in relation to another entity.
- F. None of above. chosen
Provenance (4 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_69a8862d562481908d7025a1c1f67c0d |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab173936b4819097332ee185996bbd |
completed | March 6, 2026, 6:04 p.m. |
| PD | Predicate disambiguation | batch_69aa61c9e06c819085489e00cfe72153 |
completed | March 6, 2026, 5:10 a.m. |
| PDg | Predicate description generation | batch_69ab173830a481908b67928f16f5d999 |
completed | March 6, 2026, 6:04 p.m. |
Created at: March 4, 2026, 7:31 p.m.