Triple
T36358297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hostomel |
E895409
|
entity |
| Predicate | defenderDuringConflict |
P54263
|
FINISHED |
| Object | Armed Forces of Ukraine |
—
|
NE NERFINISHED |
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: Armed Forces of Ukraine | Statement: [Hostomel, defenderDuringConflict, Armed Forces of Ukraine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defenderDuringConflict Context triple: [Hostomel, defenderDuringConflict, Armed Forces of Ukraine]
-
A.
defender
Indicates a relationship where one entity protects, guards, or supports another entity against threats, attacks, or criticism.
-
B.
defenderIn
chosen
Indicates that an entity serves as a defensive agent or protector within a specified context, situation, or domain.
-
C.
stanceDuringConflict
Indicates the position, attitude, or side an entity adopts in relation to a specific conflict or dispute.
-
D.
heldDuringConflict
Indicates that an entity maintained control, possession, or occupation of something for some duration while an identified conflict was ongoing.
-
E.
builtDuringConflict
Indicates that the construction of one entity occurred while a specified conflict or war was taking place.
- 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_69f76e5044248190b390d8887dc03254 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fb3425666081908916fcbf3b5dd907 |
completed | May 6, 2026, 12:29 p.m. |
| PD | Predicate disambiguation | batch_69fb2f5f3164819099429c2cc3d24e01 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:09 p.m.