Triple
T15626870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Purgi language |
E375699
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Balti language |
E375700
|
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 language | Statement: [Purgi language, closelyRelatedTo, Balti language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Balti language Context triple: [Purgi language, closelyRelatedTo, Balti language]
-
A.
Balti language
chosen
The Balti language is a Tibetic language spoken primarily in the Baltistan region of northern Pakistan, known for preserving many archaic features of Classical Tibetan.
-
B.
Bariai language
The Bariai language is an Austronesian language spoken by the Bariai people of New Britain in Papua New Guinea.
-
C.
Jur Beli language
Jur Beli is a lesser-known Nilotic language spoken by the Jur Beli people of South Sudan.
-
D.
Boro language
Boro language is a Tibeto-Burman language spoken primarily by the Boro people of Assam in northeastern India.
-
E.
Balantak language
The Balantak language is an Austronesian language spoken by the Balantak people of eastern Central Sulawesi, Indonesia.
- 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e9e5e248190ae54cda1fde51efb |
completed | April 16, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff678c9d8c8190be73b6e7ed558e99 |
completed | May 9, 2026, 4:57 p.m. |
Created at: April 10, 2026, 4:14 a.m.