Triple
T4009996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seán |
E90618
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Seaghan |
E292332
|
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: Seaghan | Statement: [Seán, hasVariant, Seaghan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seaghan Context triple: [Seán, hasVariant, Seaghan]
-
A.
Aisling
Aisling is a notable film or project associated with acclaimed British cinematographer Dick Pope, recognized for his visually distinctive work.
-
B.
Deidre
Deidre is a public figure best known as the wife of former Major League Baseball star Albert Pujols and for her involvement in charitable and community work.
-
C.
Ciarán
chosen
Ciarán is a masculine Irish given name of Gaelic origin, commonly borne by men in Ireland and the Irish diaspora.
-
D.
Moira
Moira is a feminine given name of Greek origin, often considered a variant of Mary and associated with meanings like "fate" or "destiny."
-
E.
Maire
Maire is the French term for a municipality’s chief elected official, equivalent to a mayor.
- 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_69aefa86c92c81908d8a610b14e22131 |
completed | March 9, 2026, 4:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b55626f19c8190af4705b1cd3b201d |
completed | March 14, 2026, 12:35 p.m. |
Created at: March 9, 2026, 3:34 p.m.