Triple
T4549904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donetsk |
E110135
|
entity |
| Predicate | populationEstimate2013 |
P3412
|
FINISHED |
| Object | about 950000 |
—
|
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: about 950000 | Statement: [Donetsk, populationEstimate2013, about 950000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: populationEstimate2013 Context triple: [Donetsk, populationEstimate2013, about 950000]
-
A.
hasPopulationAsOf
Indicates that a population count is associated with a specific point or date in time when that population figure was valid or recorded.
-
B.
hasPopulationApproximate
chosen
Indicates that an entity has an estimated or approximate population size, rather than an exact count.
-
C.
populationDemonym
Indicates the term used to refer to the people or inhabitants associated with a particular place or region.
-
D.
populationCensusYear
Indicates the specific year in which an official population census was conducted or recorded for an entity.
-
E.
countryPopulationContext
Indicates the contextual population characteristics or statistics associated with a specific country.
- 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_69bd4412524c8190be5bcc9ddee91848 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd57f3f8348190868e274ac4df87ce |
completed | March 20, 2026, 2:21 p.m. |
| PD | Predicate disambiguation | batch_69bd5223423c81908317351b58cff5f5 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:05 p.m.