Triple
T2214947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lionel Logue |
E48007
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Laurie Logue |
E177286
|
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: Laurie Logue | Statement: [Lionel Logue, hasChild, Laurie Logue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laurie Logue Context triple: [Lionel Logue, hasChild, Laurie Logue]
-
A.
Laurie Logue
chosen
Laurie Logue is one of the children of Australian speech therapist Lionel Logue, who is renowned for helping King George VI overcome his stammer.
-
B.
Laurie Parker
Laurie Parker is a film producer known for her work on the drama "North Country" and other notable Hollywood projects.
-
C.
Laurie Nolan
Laurie Nolan is the child of American sports personality and media host Katie Nolan.
-
D.
Myrtle Logue
Myrtle Logue was the wife of Australian speech therapist Lionel Logue, known for supporting him during his work with King George VI.
-
E.
Linda Fennimore
Linda Fennimore is an artist best known for creating the cover art for Stephen King’s horror novel "Pet Sematary."
- 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_69a88aa1ee708190862c8c378c41e9eb |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abbff11574819091d1b50d637ae767 |
completed | March 7, 2026, 6:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdb8d89e248190a9cd92e9f61697f8 |
completed | March 20, 2026, 9:15 p.m. |
Created at: March 4, 2026, 7:46 p.m.