Triple
T12427177
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aran Islands |
E296928
|
entity |
| Predicate | composedOf |
P402
|
FINISHED |
| Object | Inishmaan |
E607030
|
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: Inishmaan | Statement: [Aran Islands, composedOf, Inishmaan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Inishmaan Context triple: [Aran Islands, composedOf, Inishmaan]
-
A.
Inishmaan
chosen
Inishmaan is one of the Aran Islands off Ireland’s west coast, known for its traditional Irish culture, rugged limestone landscape, and strong preservation of the Irish language.
-
B.
Inishtrahull
Inishtrahull is a small, remote island off the northern coast of County Donegal in Ireland, noted for its rugged landscape, lighthouse, and rich seabird life.
-
C.
Inishgort
Inishgort is a small island located in Clew Bay off the west coast of County Mayo, Ireland.
-
D.
Mihna
The Mihna was an Islamic inquisition instituted in the 9th century that tested and persecuted scholars over their adherence to the doctrine of the createdness of the Qur’an.
-
E.
Manthara
Manthara is a pivotal character in the Indian epic Ramayana, known as Queen Kaikeyi’s scheming maid whose manipulation leads to Rama’s exile.
- 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_69d6ada0640c81908c061d7fb3d47786 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d7ccda08190be2ff1739c1c6855 |
completed | April 10, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63499061881908d25af7c3474f774 |
completed | May 2, 2026, 5:30 p.m. |
Created at: April 8, 2026, 9:55 p.m.