Triple
T6786760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bel languages |
E155826
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object |
Siar language
The Siar language is an Austronesian language spoken by the Siar people of New Ireland in Papua New Guinea.
|
E619321
|
NE FINISHED |
How this triple was built (4 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: Siar language | Statement: [Bel languages, hasMember, Siar language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Siar language Context triple: [Bel languages, hasMember, Siar language]
-
A.
Jaunsari language
Jaunsari language is an Indo-Aryan language spoken primarily in the Jaunsar-Bawar region of Uttarakhand, India.
-
B.
Sangisari language
The Sangisari language is an endangered Northwestern Iranian language spoken by a small community in northern Iran, notable for its distinct phonology and conservative grammatical features.
-
C.
Jarai language
The Jarai language is an Austronesian language spoken by the Jarai people of Vietnam’s Central Highlands and neighboring Cambodia.
-
D.
Sirionó language
The Sirionó language is an indigenous Tupian language spoken by the Sirionó people of Bolivia.
-
E.
Sarikoli language
The Sarikoli language is an Eastern Iranian Pamir language spoken primarily by the Tajik ethnic minority in China’s Xinjiang region.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Siar language Triple: [Bel languages, hasMember, Siar language]
Generated description
The Siar language is an Austronesian language spoken by the Siar people of New Ireland in Papua New Guinea.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Siar language Target entity description: The Siar language is an Austronesian language spoken by the Siar people of New Ireland in Papua New Guinea.
-
A.
Jaunsari language
Jaunsari language is an Indo-Aryan language spoken primarily in the Jaunsar-Bawar region of Uttarakhand, India.
-
B.
Sangisari language
The Sangisari language is an endangered Northwestern Iranian language spoken by a small community in northern Iran, notable for its distinct phonology and conservative grammatical features.
-
C.
Jarai language
The Jarai language is an Austronesian language spoken by the Jarai people of Vietnam’s Central Highlands and neighboring Cambodia.
-
D.
Sirionó language
The Sirionó language is an indigenous Tupian language spoken by the Sirionó people of Bolivia.
-
E.
Sarikoli language
The Sarikoli language is an Eastern Iranian Pamir language spoken primarily by the Tajik ethnic minority in China’s Xinjiang region.
- F. None of above. chosen
Provenance (5 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_69c6881770fc8190972b2906390380f5 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d28f043081909a9a9ab635785933 |
completed | March 27, 2026, 6:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c71a871a84819098891f66c6e5b579 |
completed | March 28, 2026, 12:02 a.m. |
| NEDg | Description generation | batch_69c71b6b87d8819085e6ae122f042626 |
completed | March 28, 2026, 12:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c71c00f86c819099ef6ae0766e9f3a |
completed | March 28, 2026, 12:08 a.m. |
Created at: March 27, 2026, 2:14 p.m.