Triple
T2222685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hermann Graf |
E48175
|
entity |
| Predicate | typeOfAerialVictories |
P37134
|
FINISHED |
| Object | air-to-air kills |
—
|
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: air-to-air kills | Statement: [Hermann Graf, typeOfAerialVictories, air-to-air kills]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfAerialVictories Context triple: [Hermann Graf, typeOfAerialVictories, air-to-air kills]
-
A.
numberOfAerialVictories
Indicates the count of successful aerial combat victories achieved by an entity over opposing aircraft.
-
B.
estimatedAerialVictories
Indicates an approximate count of aerial combat victories attributed to an entity, rather than an exact, confirmed total.
-
C.
airSuperiorityContribution
Indicates the extent to which an entity contributes to achieving or maintaining control of the airspace over a given area or conflict.
-
D.
aerialUnit
Indicates that the related entity functions as or is classified as an aerial unit, typically operating or acting in the air rather than on the ground or sea.
-
E.
serviceNumberOfVictories
Indicates the number of victories achieved in the context of a particular service or service-related activity.
- 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_69a88aa1ee708190862c8c378c41e9eb |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc03bfdd48190bfb96ec3e41c22dc |
completed | March 7, 2026, 6:05 a.m. |
| PD | Predicate disambiguation | batch_69abbdac31d8819092d17815e11921e9 |
completed | March 7, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69abbfe93d7c81909f1b9c1b1e3c7989 |
completed | March 7, 2026, 6:04 a.m. |
Created at: March 4, 2026, 7:47 p.m.