Triple
T36718734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luhansk |
E906985
|
entity |
| Predicate | post2014Change |
P186191
|
FINISHED |
| Object | subject to de facto separation from Ukrainian central authorities |
—
|
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: subject to de facto separation from Ukrainian central authorities | Statement: [Luhansk, post2014Change, subject to de facto separation from Ukrainian central authorities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: post2014Change Context triple: [Luhansk, post2014Change, subject to de facto separation from Ukrainian central authorities]
-
A.
post2020Change
Indicates a change, update, or event that occurred after the year 2020.
-
B.
post1993Change
Indicates a change or modification that occurred after the year 1993.
-
C.
post2020Status
Indicates the status or condition of an entity specifically in the period after the year 2020.
-
D.
changedInYear
Indicates that an entity underwent a change or modification during a specified calendar year.
-
E.
MPIn2014
Indicates that an entity served as a Member of Parliament (MP) in the year 2014.
- F. None of above. chosen
Provenance (4 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_69f76e73ad108190a5241585f2303e9a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c8421b248190a171972072f16828 |
completed | May 3, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
| PDg | Predicate description generation | batch_69f7c776b4088190bef550c869da530d |
completed | May 3, 2026, 10:08 p.m. |
Created at: May 3, 2026, 4:12 p.m.