Triple
T34728784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Azovstal Iron and Steel Works |
E1001146
|
entity |
| Predicate | wasStrongholdFor |
P46785
|
FINISHED |
| Object | Ukrainian Armed Forces |
—
|
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: Ukrainian Armed Forces | Statement: [Azovstal Iron and Steel Works, wasStrongholdFor, Ukrainian Armed Forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasStrongholdFor Context triple: [Azovstal Iron and Steel Works, wasStrongholdFor, Ukrainian Armed Forces]
-
A.
strongholdOf
chosen
Indicates that a location serves as a primary fortified base, center of power, or main stronghold for a particular entity.
-
B.
wasFortifiedBy
Indicates that a place or structure received defensive strengthening or fortification through the actions or resources of a specified agent or entity.
-
C.
historicalStronghold
Indicates that a location has historically served as a fortified center of power, defense, or control for a group or authority.
-
D.
wasCitadelOf
Indicates that a place previously served as the main fortified stronghold or central defensive structure for another entity.
-
E.
primaryStronghold
Indicates that one location serves as the main base, fortress, or central stronghold for an entity compared to its other sites.
- 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.