Triple
T15412128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Fromelles |
E368618
|
entity |
| Predicate | killedAustralianSoldiers |
P118692
|
FINISHED |
| Object | over 1,900 Australians killed |
—
|
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 1,900 Australians killed | Statement: [Battle of Fromelles, killedAustralianSoldiers, over 1,900 Australians killed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: killedAustralianSoldiers Context triple: [Battle of Fromelles, killedAustralianSoldiers, over 1,900 Australians killed]
-
A.
casualtiesUKKilled
Indicates that the relationship specifies the number of people from the UK who were killed in the referenced event or incident.
-
B.
sonsKilledBy
Indicates that the referenced sons are those who were killed by the specified agent or entity.
-
C.
BoerCasualties
Indicates the number or occurrence of casualties suffered by Boer forces in a conflict or engagement.
-
D.
numberOfBrothersKilledInWar
Indicates the count of a person’s brothers who were killed while serving in a war.
-
E.
allegedToHaveKilled
Indicates that one entity is claimed or accused, but not proven, to have killed 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_69d85a16c68c819099c1b547fbc87b32 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03ea600b48190a3dbca1a68a2a1cd |
completed | April 16, 2026, 1:43 a.m. |
| PD | Predicate disambiguation | batch_69ded27f45548190a6d2b1b85cb47444 |
completed | April 14, 2026, 11:49 p.m. |
| PDg | Predicate description generation | batch_69ded57005608190886cd01f640dfedb |
completed | April 15, 2026, 12:01 a.m. |
Created at: April 10, 2026, 3:20 a.m.