Triple
T38081909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2004 Georgian presidential election |
E950873
|
entity |
| Predicate | heldInCapitalCity |
P5025
|
FINISHED |
| Object | Tbilisi |
—
|
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: Tbilisi | Statement: [2004 Georgian presidential election, heldInCapitalCity, Tbilisi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldInCapitalCity Context triple: [2004 Georgian presidential election, heldInCapitalCity, Tbilisi]
-
A.
observedInCapital
Indicates that an entity was observed, recorded, or took place within the capital city of a specified political or administrative region.
-
B.
usedInCapitalCityOf
Indicates that something is utilized or applied within the capital city of a specified region or country.
-
C.
isPartOfCapitalCityOf
Indicates that something is a constituent or component of the capital city belonging to a particular political or administrative entity.
-
D.
locatedInCapital
chosen
Indicates that an entity is situated within the capital city of a specified region, country, or administrative area.
-
E.
containsCapitalCity
Indicates that a geographic or political region includes within its boundaries the capital city associated with it.
- 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_69f76f03a3608190a73fd6df87c792a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.