Triple
T9660547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German surrender at Khorab |
E233576
|
entity |
| Predicate | commanderNationalitySide1 |
P10573
|
FINISHED |
| Object | South African |
—
|
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: South African | Statement: [German surrender at Khorab, commanderNationalitySide1, South African]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commanderNationalitySide1 Context triple: [German surrender at Khorab, commanderNationalitySide1, South African]
-
A.
commanderNationality
chosen
Indicates the national affiliation or citizenship of a given commander.
-
B.
combatantsNationality
Indicates that the entities involved in a combat or conflict share or are associated with a specified nationality.
-
C.
notableCommanderSide
Indicates that a particular military or strategic side is notably commanded or led by a specified commander.
-
D.
commandersSide
Indicates that one entity is on the same side, faction, or team as the commander in a conflict or competitive context.
-
E.
commanderForSovietSide
Indicates that an entity serves as a military commander representing or leading forces on the Soviet side in a conflict or operation.
- 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_69ca848d3b6c8190ae98ea554dea58df |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9c08d0d0819086426ad6891b18db |
completed | April 1, 2026, 10:28 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b3239c8190b3ae3b9bd121e4bd |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:14 p.m.