Triple
T7219643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erromango |
E150222
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Upongkor |
E649680
|
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: Upongkor | Statement: [Erromango, hasSettlement, Upongkor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Upongkor Context triple: [Erromango, hasSettlement, Upongkor]
-
A.
Upongkor
chosen
Upongkor is the principal settlement and main population center on the island of Erromango in Vanuatu.
-
B.
Korekore
Korekore is a major dialect of the Shona language spoken primarily in northern Zimbabwe.
-
C.
Ōpunake
Ōpunake is a small coastal town on the west coast of New Zealand’s North Island, known for its surf beach and views of Mount Taranaki.
-
D.
Pipikoro
Pipikoro is an Austronesian language spoken in Central Sulawesi, Indonesia, known locally as an alternate name for the Uma language.
-
E.
Pangim
Pangim, also known as Panaji, is the riverside city that serves as the administrative and cultural center of the Indian state of Goa.
- 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_69c687effb44819092b95d07d0368c9f |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e9b1a7908190bd215ffb84592e32 |
completed | March 27, 2026, 8:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7d38423bc8190aaf4ee3940813d33 |
completed | March 28, 2026, 1:11 p.m. |
Created at: March 27, 2026, 2:53 p.m.