Triple
T23405876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zavkhan Province |
E559931
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Uliastai |
—
|
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: Uliastai | Statement: [Zavkhan Province, hasSettlement, Uliastai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Uliastai Context triple: [Zavkhan Province, hasSettlement, Uliastai]
-
A.
Uliastai
chosen
Uliastai is a historic town in western Mongolia that serves as an important regional center for administration and trade.
-
B.
Perdizes
Perdizes is a central district in São Paulo, Brazil, known for its residential character, cultural venues, and proximity to major sports and educational institutions.
-
C.
Prauliena
Prauliena is a village and administrative unit located within Madona Municipality in eastern Latvia.
-
D.
Lutai
Lutai is the historical site in ancient China traditionally regarded as the place where the last Shang dynasty ruler, King Zhou of Shang, met his end.
-
E.
Nausėda
Nausėda is a Lithuanian surname most prominently associated with Gitanas Nausėda, the President of Lithuania.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a4e364548190b98dc09240fba58e |
completed | April 29, 2026, 6:27 a.m. |
Created at: April 17, 2026, 5:38 p.m.