Triple
T14406525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bakhmut |
E357210
|
entity |
| Predicate | battleIntensity |
P89222
|
FINISHED |
| Object | site of prolonged urban warfare 2022–2023 |
—
|
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: site of prolonged urban warfare 2022–2023 | Statement: [Bakhmut, battleIntensity, site of prolonged urban warfare 2022–2023]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: battleIntensity Context triple: [Bakhmut, battleIntensity, site of prolonged urban warfare 2022–2023]
-
A.
battleScale
chosen
Indicates the relative size or intensity of a battle, such as how large, extensive, or severe the conflict is.
-
B.
battleOccurred
Indicates that a conflict or combat event took place between specified parties at a particular time and/or location.
-
C.
combatPace
Indicates the speed, intensity, or tempo at which combat or a battle is being conducted between opposing forces.
-
D.
battleTarget
Indicates that one entity is the chosen opponent or objective that another entity is engaging or intends to engage in battle.
-
E.
battleDuration
Indicates the length of time for which a particular battle or combat event lasts.
- 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_69d82793421c8190861eb0e673b085de |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de908804048190a4fe58afc2e0a5b6 |
completed | April 14, 2026, 7:07 p.m. |
| PD | Predicate disambiguation | batch_69de2aa1b57881909a033eac8545c417 |
completed | April 14, 2026, 11:53 a.m. |
Created at: April 10, 2026, 1:17 a.m.