Triple
T38324216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tartar region |
E1036736
|
entity |
| Predicate | partiallyOccupiedDuring |
P61153
|
FINISHED |
| Object | First Nagorno-Karabakh War |
—
|
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: First Nagorno-Karabakh War | Statement: [Tartar region, partiallyOccupiedDuring, First Nagorno-Karabakh War]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partiallyOccupiedDuring Context triple: [Tartar region, partiallyOccupiedDuring, First Nagorno-Karabakh War]
-
A.
wasOccupiedDuring
Indicates that an entity was under the control, presence, or use of another entity throughout a specified time period.
-
B.
wasPartiallyOccupiedBy
chosen
Indicates that an entity was, for a limited extent or portion of its space or duration, occupied or taken up by another entity.
-
C.
partiallyHeldAt
Indicates that an entity is held or grasped in an incomplete, unstable, or not fully secure manner at a particular time or location.
-
D.
partiallyOn
Indicates that one entity rests or extends over another such that only a portion of its area, volume, or length is supported or in contact.
-
E.
occupiedFrom
Indicates that an entity is in use or inhabited starting from a specified point in time.
- 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_69f76e1c16fc8190bde982289dd5106b |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd4f39b5008190b83b3227ce22c509 |
completed | May 8, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69fd4df17c548190a4e2a6fea70f7e10 |
completed | May 8, 2026, 2:44 a.m. |
Created at: May 3, 2026, 4:30 p.m.