Triple
T22241215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yazgulyam |
E549726
|
entity |
| Predicate | neighboringLanguage |
P16383
|
FINISHED |
| Object | Bartangi |
—
|
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: Bartangi | Statement: [Yazgulyam, neighboringLanguage, Bartangi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bartangi Context triple: [Yazgulyam, neighboringLanguage, Bartangi]
-
A.
Bartangi
chosen
Bartangi is a lesser-known Eastern Iranian language spoken in the Bartang Valley region of Tajikistan.
-
B.
Tharbogang
Tharbogang is a rural locality within the City of Griffith in New South Wales, Australia, known for its agricultural production.
-
C.
Dundaga
Dundaga is a small historic town in western Latvia known for its medieval castle and scenic surroundings in the Kurzeme region.
-
D.
Birketveit
Birketveit is a village in Agder county, Norway, serving as the main local hub for municipal services and community life in Iveland.
-
E.
Tongrinne
Tongrinne is a village in the Walloon region of Belgium that forms one of the municipal sections of the municipality of Sombreffe in the province of Namur.
- 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_69e11e41d9408190bd770cf282e22753 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f132140ed481909ab0d4022756a4ba |
completed | April 28, 2026, 10:17 p.m. |
Created at: April 16, 2026, 8:38 p.m.