Triple
T14562365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Tondibi |
E341697
|
entity |
| Predicate | MoroccanForceStrength |
P83916
|
FINISHED |
| Object | approximately 4,000 to 5,000 men |
—
|
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 4,000 to 5,000 men | Statement: [Battle of Tondibi, MoroccanForceStrength, approximately 4,000 to 5,000 men]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MoroccanForceStrength Context triple: [Battle of Tondibi, MoroccanForceStrength, approximately 4,000 to 5,000 men]
-
A.
MoroccanStrengthApprox
chosen
Indicates an approximate assessment or estimation of the strength associated with Morocco or Moroccan-related entities.
-
B.
CarthaginianForceType
Indicates the type or classification of a Carthaginian military force involved in a given context or event.
-
C.
MoroccanRuler
Indicates a person holds or held the position of ruler over Morocco.
-
D.
commandingForce2Strength
Indicates that a commanding force possesses or exerts a particular level or measure of strength.
-
E.
estimatedCarthaginianForces
Indicates an assessment or approximation of the size or strength of the military forces associated with Carthage.
- 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_69d822dcc6248190bed689984bceb0e2 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb38afa8881909c9151b7620949ae |
completed | April 14, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69de5c57489c8190b57917be1dba6ae6 |
completed | April 14, 2026, 3:25 p.m. |
Created at: April 10, 2026, 1:23 a.m.