Triple
T16874595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lavezzi Islands |
E421265
|
entity |
| Predicate | nearestTown |
P350
|
FINISHED |
| Object | Bonifacio |
E102929
|
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: Bonifacio | Statement: [Lavezzi Islands, nearestTown, Bonifacio]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bonifacio Context triple: [Lavezzi Islands, nearestTown, Bonifacio]
-
A.
Bonifacio
chosen
Bonifacio is a historic fortified town perched on dramatic limestone cliffs at the southern tip of Corsica, overlooking the Strait of Bonifacio between the island and Sardinia.
-
B.
Diosdado
Diosdado is a Filipino given name most prominently associated with Diosdado Macapagal, the ninth President of the Philippines.
-
C.
Niceto
Niceto is the given name of Niceto Alcalá-Zamora, the first President of the Second Spanish Republic.
-
D.
Alfonso Oiterong
Alfonso Oiterong was a Palauan politician who briefly served as the country's president during its early years of independence.
-
E.
Ramiro
Ramiro is a masculine given name of Spanish and Portuguese origin, historically borne by several medieval kings and nobles in the Iberian Peninsula.
- 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_69d889d470fc8190b4aec199636c0c56 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3b7f5290481909e0fd0af30935fcd |
completed | April 18, 2026, 4:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c2b2e67c81908e2313491d16353f |
completed | May 10, 2026, 5:38 p.m. |
Created at: April 10, 2026, 5:29 a.m.