Triple
T9707883
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tyrrhenian Sea coast |
E234944
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object | Elba |
E21661
|
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: Elba | Statement: [Tyrrhenian Sea coast, hasIsland, Elba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elba Context triple: [Tyrrhenian Sea coast, hasIsland, Elba]
-
A.
Elba
chosen
Elba is a Mediterranean island off the coast of Italy, best known as the site of Napoleon Bonaparte’s first exile in 1814–1815.
-
B.
Isola di Pianosa
Isola di Pianosa is a small, flat Italian island in the Tuscan Archipelago, known for its former high-security prison and largely untouched natural environment.
-
C.
Capraia
Capraia is a small, rugged Italian island in the Tyrrhenian Sea known for its volcanic landscape, clear waters, and protected natural environment.
-
D.
Île de la Pietra
Île de la Pietra is a small rocky island off the coast of L’Île-Rousse in Corsica, known for its scenic lighthouse, red granite cliffs, and panoramic sea views.
-
E.
Isola del Mare
Isola del Mare is a small Italian seaside town featured in Pixar’s film “Luca,” serving as the primary human setting where much of the story unfolds.
- 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_69ca84cc78808190a56f3402b7c139a7 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9da5e09081909456909d768611e6 |
completed | April 1, 2026, 10:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1bcc0117c8190bc82a985ce59623d |
completed | April 5, 2026, 1:37 a.m. |
Created at: March 30, 2026, 8:19 p.m.