Triple
T30074808
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2/43rd Battalion (Australia) |
E764288
|
entity |
| Predicate | warHonour |
P12198
|
FINISHED |
| Object | Tobruk 1941 |
—
|
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: Tobruk 1941 | Statement: [2/43rd Battalion (Australia), warHonour, Tobruk 1941]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: warHonour Context triple: [2/43rd Battalion (Australia), warHonour, Tobruk 1941]
-
A.
honourOf
Indicates that one entity is the source, bearer, or cause of another entity’s honor, prestige, or distinguished recognition.
-
B.
battleHonoursInheritedFrom
Indicates that one entity’s battle honours are derived from, or passed down through, another entity’s battle honours.
-
C.
honoursMilitaryService
Indicates that one entity formally recognizes and pays tribute to the military service performed by another entity.
-
D.
battleHonors
chosen
Indicates that an entity has been awarded or is associated with specific honors or distinctions earned through participation in battles or military engagements.
-
E.
battleHonoursCount
Indicates the number of battle honours associated with an entity, such as a military unit, ship, or individual.
- 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_69f22472eee081909791dc372aa766e9 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67d3cbff081909d4e64ee63f43ea5 |
completed | May 2, 2026, 10:39 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:01 p.m.