Triple
T8648250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Australian Imperial Force |
E205032
|
entity |
| Predicate | approximateWounded |
P25887
|
FINISHED |
| Object | over 150000 wounded |
—
|
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 150000 wounded | Statement: [Australian Imperial Force, approximateWounded, over 150000 wounded]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateWounded Context triple: [Australian Imperial Force, approximateWounded, over 150000 wounded]
-
A.
hasApproximateNumberOfWounds
Indicates that an entity has a number of wounds that is known only approximately rather than as an exact count.
-
B.
wasWoundedIn
Indicates that an entity sustained an injury as a result of a specified event, situation, or conflict.
-
C.
injuriesApprox
chosen
Indicates an approximate or estimated number or extent of injuries associated with an event or entity.
-
D.
killedOrMortallyWounded
Indicates that one entity caused the death of, or inflicted injuries certain to result in the death of, another entity.
-
E.
damageTo
Indicates a relationship where one entity causes harm, loss, or deterioration to another entity.
- 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_69ca834e56848190abb0eeaec9dedd32 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4812b7bc8190acb40da57cad293a |
completed | March 31, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69cc45619460819091e83ffdec99c865 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:29 p.m.