Triple
T34728795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Azovstal Iron and Steel Works |
E1001146
|
entity |
| Predicate | hadCiviliansSheltering |
P77310
|
FINISHED |
| Object | Ukrainian civilians |
—
|
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: Ukrainian civilians | Statement: [Azovstal Iron and Steel Works, hadCiviliansSheltering, Ukrainian civilians]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadCiviliansSheltering Context triple: [Azovstal Iron and Steel Works, hadCiviliansSheltering, Ukrainian civilians]
-
A.
hadSanctuaryOf
Indicates that an entity possessed or hosted a sanctuary dedicated to another entity.
-
B.
civilianDisplacement
Indicates the forced or compelled movement of civilian populations from their homes or usual places of residence, typically due to conflict, violence, or persecution.
-
C.
hasHardenedShelters
Indicates that an entity possesses or is equipped with shelters that are reinforced or hardened for protection.
-
D.
wasBombedDuring
Indicates that an entity was subjected to a bombing attack during a specified event or time period.
-
E.
sheltersPeopleFleeing
chosen
Indicates that an entity provides refuge or protection to people who are escaping danger, persecution, or adverse conditions.
- 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_69f76daeb6e48190a4c9a6b0edc80f72 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f77ffa6b68819090257fed3802c239 |
completed | May 3, 2026, 5:03 p.m. |
| PD | Predicate disambiguation | batch_69f7795978c481909e152cd1bd02dd07 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 3, 2026, 3:59 p.m.