Triple
T4009387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. John’s |
E90605
|
entity |
| Predicate | locatedOnIsland |
P970
|
FINISHED |
| Object | Antigua |
E82884
|
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: Antigua | Statement: [St. John’s, locatedOnIsland, Antigua]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Antigua Context triple: [St. John’s, locatedOnIsland, Antigua]
-
A.
Antigua
Antigua is a municipality located on the island of Fuerteventura in Spain’s Canary Islands, known for its traditional architecture and rural landscapes.
-
B.
Antigua
chosen
Antigua is a Caribbean island nation renowned for its numerous white-sand beaches, coral reefs, and role as a major tourist destination in the Lesser Antilles.
-
C.
San Cristóbal
San Cristóbal is a municipality in western Cuba located within Artemisa Province.
-
D.
San Cristóbal
San Cristóbal is an active stratovolcano in northwestern Nicaragua and one of the most prominent and frequently erupting volcanoes in the Central American region.
-
E.
Grenada
Grenada is a small Caribbean island nation known for its spice production, picturesque beaches, and lush mountainous interior.
- 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_69aed95e44088190aff7d90a151b1b20 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefa8579288190940487ad07e38de0 |
completed | March 9, 2026, 4:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b54c6ae0ec819099c229a4cfe926f2 |
completed | March 14, 2026, 11:54 a.m. |
Created at: March 9, 2026, 3:34 p.m.