Triple
T4273279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Enya |
E96987
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | Clannad |
E426472
|
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: Clannad | Statement: [Enya, associatedAct, Clannad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clannad Context triple: [Enya, associatedAct, Clannad]
-
A.
Clannad
chosen
Clannad is an Irish family band from County Donegal known for pioneering a distinctive blend of traditional Celtic music, folk, and ethereal new-age sounds.
-
B.
A’ Chill
A’ Chill is a historic abandoned village and former main settlement on the Scottish island of Canna in the Inner Hebrides.
-
C.
De Dannan
De Dannan is an influential Irish traditional music group known for its innovative arrangements and for launching the careers of several prominent Irish singers and musicians.
-
D.
The Cavanaughs
The Cavanaughs is an American television sitcom best known for featuring actress Christine Ebersole in a prominent role.
-
E.
Carn a’ Ghaill
Carn a’ Ghaill is the summit that forms the highest point on the Scottish island of Canna in the Inner Hebrides.
- 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_69b34544be3c819084d1ab82d29f90c5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34ffe44508190875d734eb18dfb87 |
completed | March 12, 2026, 11:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5c71fc0bc8190922ae85d3bd23546 |
completed | March 14, 2026, 8:37 p.m. |
Created at: March 12, 2026, 11:07 p.m.