Triple
T11671839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Cristobal |
E277400
|
entity |
| Predicate | formerNameOf |
P65
|
FINISHED |
| Object | Makira |
E57264
|
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: Makira | Statement: [San Cristobal, formerNameOf, Makira]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Makira Context triple: [San Cristobal, formerNameOf, Makira]
-
A.
Makira
chosen
Makira is a large, rugged island in the Solomon Islands known for its rich biodiversity, traditional Melanesian cultures, and relatively undeveloped, rainforest-covered interior.
-
B.
Makuti
Makuti is a small settlement in northern Zimbabwe that serves as a key junction and rest stop on the main road between Harare, Kariba, and Chirundu.
-
C.
Malanga
Malanga is a surname most notably associated with Gerard Malanga, an American poet, photographer, and key collaborator of artist Andy Warhol.
-
D.
Khaya
Khaya is a genus of tropical African trees in the mahogany family, valued for their high-quality timber.
-
E.
Fagara
Fagara is a genus of flowering plants in the citrus family Rutaceae, known for species that often have aromatic properties and spiny stems.
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a44264c08190ba1a4a5bcdc9367b |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef13d3a8608190a084d8bbcac4f924 |
completed | April 27, 2026, 7:44 a.m. |
Created at: April 8, 2026, 9:40 p.m.