Triple
T19674333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Gilboa |
E472412
|
entity |
| Predicate | militaryTacticUsedByPhilistines |
P100860
|
FINISHED |
| Object | archery |
—
|
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: archery | Statement: [Battle of Gilboa, militaryTacticUsedByPhilistines, archery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryTacticUsedByPhilistines Context triple: [Battle of Gilboa, militaryTacticUsedByPhilistines, archery]
-
A.
militaryTacticsUsed
Indicates that specific military tactics are employed or applied in the context of a particular operation, conflict, or strategic situation.
-
B.
wasPhilistineCity
Indicates that the subject was a city belonging to or associated with the Philistines.
-
C.
PersianTactics
Indicates the use or application of military strategies, maneuvers, or methods characteristic of Persian forces in a conflict or battle context.
-
D.
militaryTacticsFaced
Indicates that an entity encountered or had to contend with specific military tactics employed by another entity.
-
E.
tacticalFeatureUsed
chosen
Indicates that a specific tactical feature, maneuver, or capability is employed or brought into play within a tactical situation or operation.
- 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6416e19d881909248c4f778f7147a |
completed | April 20, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_69e514eb37b8819091502cc954f70eba |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:45 p.m.