Triple
T14304443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baluan Island |
E354655
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object | Titan language |
E929404
|
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: Titan language | Statement: [Baluan Island, hasLanguage, Titan language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Titan language Context triple: [Baluan Island, hasLanguage, Titan language]
-
A.
Titan language
chosen
Titan language is an Austronesian language spoken by the Manus people of Manus Island in Papua New Guinea.
-
B.
Mono language
Mono language is a Native American Uto-Aztecan language traditionally spoken by the Mono people of eastern California.
-
C.
Pear language
Pear language is an Austroasiatic language of the Pearic branch spoken by the Pear people of Cambodia and considered highly endangered.
-
D.
Temiar language
The Temiar language is an Austroasiatic Aslian language spoken by the Temiar people of Peninsular Malaysia, known for its complex phonology and rich oral tradition.
-
E.
Mimi-D language
Mimi-D is an extinct and poorly documented language of Chad, historically spoken by a small ethnic group and only fragmentarily known from early 20th-century records.
- 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_69d8278ed42c8190b9f882dcce611347 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de85afabe48190926d6098047f4bcf |
completed | April 14, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd3d2a56a4819095b5c2164b1ad9fb |
completed | May 8, 2026, 1:32 a.m. |
Created at: April 10, 2026, 1:12 a.m.