Triple
T9526609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harari language |
E229774
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Zay language |
E397423
|
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: Zay language | Statement: [Harari language, closelyRelatedTo, Zay language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zay language Context triple: [Harari language, closelyRelatedTo, Zay language]
-
A.
Zay language
chosen
Zay language is a South Ethiopic Semitic language spoken by the Zay people on islands and shores of Lake Zway in Ethiopia.
-
B.
Zaiwa language
The Zaiwa language is a Tibeto-Burman language spoken primarily by the Zaiwa people in parts of Yunnan, China and northern Myanmar.
-
C.
Zabana language
The Zabana language is an Oceanic language spoken primarily on Santa Isabel Island in the Solomon Islands.
-
D.
Yazgulyam language
The Yazgulyam language is an Eastern Iranian language spoken by a small community in Tajikistan’s Yazgulyam Valley, notable for preserving many archaic features within the Pamir language group.
-
E.
Lundayeh language
The Lundayeh language is an Austronesian language spoken by the Lundayeh (Lun Bawang) people of northern Borneo, primarily in parts of Malaysia and 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_69ca8479934c81908006d0e6e970ae05 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd989c831081908877e42f7ead84ba |
completed | April 1, 2026, 10:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d14c2710b481909a13d946f6dd5b2d |
completed | April 4, 2026, 5:36 p.m. |
Created at: March 30, 2026, 8 p.m.