Triple
T13466587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Turtuk |
E311516
|
entity |
| Predicate | languageSpoken |
P151
|
FINISHED |
| Object | Balti |
E77468
|
NE 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: Balti | Statement: [Turtuk, languageSpoken, Balti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Balti Context triple: [Turtuk, languageSpoken, Balti]
-
A.
Balti
chosen
Balti is a Tibetic language spoken primarily in the Baltistan region of northern Pakistan and parts of Ladakh, India.
-
B.
Bakkhali
Bakkhali is a seaside town and beach resort on the Bay of Bengal in the Indian state of West Bengal, known for its tranquil beaches and scenic coastal views.
-
C.
Bukhori
Bukhori is a Jewish dialect of Tajik Persian traditionally spoken by the Bukharan Jewish community of Central Asia.
-
D.
Mehunaise
Mehunaise is the French demonym for a female inhabitant of the town of Mehun-sur-Yèvre in central France.
-
E.
Khinkali
Khinkali is a popular Georgian dumpling typically filled with spiced meat and broth, known for its distinctive twisted top and eaten by hand.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d806a938b8819097ec43a2229fc7f9 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf101a1081909f2aba6da47baacc |
completed | April 12, 2026, 2:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f746282318819090e47c324807dc1e |
completed | May 3, 2026, 12:57 p.m. |
Created at: April 9, 2026, 9:42 p.m.