Triple
T17274398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheelagh |
E419347
|
entity |
| Predicate | relatedName |
P3889
|
FINISHED |
| Object | Sheila |
—
|
NE NERFINISHED |
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: Sheila | Statement: [Sheelagh, relatedName, Sheila]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sheila Context triple: [Sheelagh, relatedName, Sheila]
-
A.
Sheila
chosen
Sheila is a feminine given name of Irish origin that has been widely used in English-speaking countries.
-
B.
Sheila Darcy
Sheila Darcy was an American film actress best known for her roles in 1930s and 1940s Hollywood B-movies and serials.
-
C.
Sally Hibbin
Sally Hibbin is a British film and television producer known for her collaborations with director Ken Loach and her work on socially conscious, independent films.
-
D.
Gillian
Gillian is a feminine given name of Latin origin, commonly used in English-speaking countries.
-
E.
Mary Collins
Mary Collins is a British immunologist and academic known for her work in gene therapy and for being married to Nobel Prize–winning biochemist Tim Hunt.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e4332566c08190b4495dbbfe310ab6 |
completed | April 19, 2026, 1:43 a.m. |
Created at: April 10, 2026, 5:40 a.m.