Triple
T20723730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Debaltseve |
E509381
|
entity |
| Predicate | post2014Status |
P48142
|
FINISHED |
| Object | frontline city in the war in Donbas |
—
|
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: frontline city in the war in Donbas | Statement: [Debaltseve, post2014Status, frontline city in the war in Donbas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: post2014Status Context triple: [Debaltseve, post2014Status, frontline city in the war in Donbas]
-
A.
post2009Status
Indicates the status or condition of an entity specifically in the period after the year 2009.
-
B.
post2000Status
Indicates whether a given entity’s status, condition, or classification applies specifically to the period after the year 2000.
-
C.
statusAfter2014
chosen
Indicates the condition or state of an entity as it exists from the year 2014 onward, typically in contrast to its prior status.
-
D.
post2005Status
Indicates the status or condition of an entity specifically in the period after the year 2005.
-
E.
registrationStatusAfter2014
Indicates the registration status of an entity specifically for the period after the year 2014.
- 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_69e0b4c4cc648190b45fda6e2b20af56 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1e59b2081909fb6c29cb5018bb4 |
completed | April 21, 2026, 12:16 a.m. |
| PD | Predicate disambiguation | batch_69e5c04b31248190b9b9d91b5cb854e3 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:28 p.m.