Triple
T12835609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mili Atoll |
E306903
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Likiep-en-Mili |
E328184
|
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: Likiep-en-Mili | Statement: [Mili Atoll, hasSettlement, Likiep-en-Mili]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Likiep-en-Mili Context triple: [Mili Atoll, hasSettlement, Likiep-en-Mili]
-
A.
Likiep
chosen
Likiep is a settlement in the Marshall Islands that serves as the main population center and administrative hub of Likiep Atoll.
-
B.
Mahorais
Mahorais is a French-based creole language spoken primarily on the island of Mayotte in the Indian Ocean.
-
C.
Tasiilaq
Tasiilaq is a remote town on the southeastern coast of Greenland, known for its dramatic fjord landscape, Inuit culture, and role as a regional hub for outdoor and Arctic expeditions.
-
D.
Mokena
Mokena is a suburban village in Will County, Illinois, located southwest of Chicago.
-
E.
Lealui
Lealui is the dry-season capital and royal residence of the Litunga, the king of Barotseland, located on the Zambezi floodplain in western Zambia.
- 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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96fb1c7248190bb6e644e041d192e |
completed | April 10, 2026, 9:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68edaa6288190a775f6e852fa941b |
completed | May 2, 2026, 11:55 p.m. |
Created at: April 9, 2026, 5:35 p.m.