Triple
T21473634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mortlock |
E529795
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Mortlockese |
—
|
NE NERFINISHED |
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: Mortlockese | Statement: [Mortlock, hasAlternativeName, Mortlockese]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mortlockese Context triple: [Mortlock, hasAlternativeName, Mortlockese]
-
A.
Mortlockese language
chosen
Mortlockese is an Austronesian language of the Chuukic branch spoken primarily in the Mortlock Islands of Chuuk State in the Federated States of Micronesia.
-
B.
Camorta language
The Camorta language is an Austroasiatic language spoken by the Nicobarese people on Camorta Island in India’s Nicobar Islands.
-
C.
Saraveca language
The Saraveca language is an extinct Arawakan language once spoken in Bolivia, known from very limited historical documentation.
-
D.
Tuvinian language
The Tuvinian language is a Turkic language spoken primarily in the Tuva Republic of Russia, known for its rich oral traditions and use in Tuvan throat singing culture.
-
E.
Damara language
The Damara language is a Khoe (Central Khoisan) language spoken primarily by the Damara people of Namibia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c459acb481909bb6ee452a0045c7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea156dac819087c4594d022d3df6 |
completed | April 23, 2026, 9:44 a.m. |
Created at: April 16, 2026, 6:19 p.m.