Triple
T11862731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kodori Gorge |
E282197
|
entity |
| Predicate | populationBeforeConflict |
P23346
|
FINISHED |
| Object | predominantly Svan |
—
|
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: predominantly Svan | Statement: [Kodori Gorge, populationBeforeConflict, predominantly Svan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: populationBeforeConflict Context triple: [Kodori Gorge, populationBeforeConflict, predominantly Svan]
-
A.
formerPopulation
chosen
Indicates that an entity once had a certain population value or size during a past time period but no longer does.
-
B.
permanentPopulation
Indicates that an entity has a stable, long-term resident population rather than a temporary or transient presence.
-
C.
populationEstimatePreContact
Indicates an estimated size of a population before initial contact occurred between that population and an external group (such as colonizers, explorers, or another culture).
-
D.
dividedPopulationOf
Indicates that a population has been split into distinct subgroups or segments, typically based on specified criteria or characteristics.
-
E.
populationScale
Indicates the relative size or magnitude of a population, typically categorizing it into broad scale levels (e.g., small, medium, large).
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a69b16bc8190999a0c1240f9ce6a |
completed | April 10, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69d8a2573dbc8190ab432e8e28fde6cc |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:43 p.m.