Triple
T33097499
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lysychansk |
E846949
|
entity |
| Predicate | wasFrontlineCityIn |
P76979
|
FINISHED |
| Object | War in Donbas |
—
|
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: War in Donbas | Statement: [Lysychansk, wasFrontlineCityIn, War in Donbas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasFrontlineCityIn Context triple: [Lysychansk, wasFrontlineCityIn, War in Donbas]
-
A.
hadCity
Indicates that an entity was formerly associated with or located in a particular city.
-
B.
frontLineCity
chosen
Indicates that a city is located on or very near an active military front line, directly exposed to ongoing or imminent conflict.
-
C.
wasCitadelOf
Indicates that a place previously served as the main fortified stronghold or central defensive structure for another entity.
-
D.
wasFrontierTownIn
Indicates that a town functioned as a frontier settlement within a specified region or territorial jurisdiction.
-
E.
wasStrategicCenterIn
Indicates that an entity functioned as a key strategic center or hub within a specified context, such as a region, period, or conflict.
- 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_69f3495590dc8190aa04f3dec74ce976 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d6a9d12881908087ba7b04049ec0 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:26 a.m.