Triple
T1299608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Crete |
E27730
|
entity |
| Predicate | AlliedCasualtiesApprox |
P17247
|
FINISHED |
| Object | over 15,000 captured |
—
|
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: over 15,000 captured | Statement: [Battle of Crete, AlliedCasualtiesApprox, over 15,000 captured]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AlliedCasualtiesApprox Context triple: [Battle of Crete, AlliedCasualtiesApprox, over 15,000 captured]
-
A.
casualtiesAllied
chosen
Indicates the number or extent of losses (killed, wounded, or missing) suffered by allied forces in a conflict or incident.
-
B.
troopStrengthAlliedApprox
Indicates that the approximate troop strength of one entity is being assessed or reported in relation to its allied forces.
-
C.
militaryCasualtiesEstimate
Indicates an estimated number of people killed, wounded, or missing as a result of military conflict or operations.
-
D.
NATOcasualtiesMilitaryKilled
Indicates that members of NATO military forces were killed as casualties.
-
E.
alliedForcesComposition
Indicates the makeup and relative proportions of different military or paramilitary groups that are joined together as allied forces in a given context.
- 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_69a496d6682881909ba658f1c1e0e2b0 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c11314a48190ab4efb8b1acdce50 |
completed | March 1, 2026, 10:43 p.m. |
| PD | Predicate disambiguation | batch_69a4bee8544c8190874efd9bae9bccf9 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:51 p.m.