Triple
T17876584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kate Read |
E446968
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Grandma Thora |
—
|
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: Grandma Thora | Statement: [Kate Read, relative, Grandma Thora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grandma Thora Context triple: [Kate Read, relative, Grandma Thora]
-
A.
Grandma Thora
chosen
Grandma Thora is a kindly, elderly character in the Arthur children's book and television series, known as Arthur and D.W. Read’s grandmother who often offers them warmth, wisdom, and homemade treats.
-
B.
Thora
Thora is a small rural locality in New South Wales, Australia, situated in the Bellingen Valley near the Bellinger River.
-
C.
Hulda
Hulda is a feminine given name of Germanic origin, historically used in Scandinavian and German-speaking countries.
-
D.
Thora Hird
Thora Hird was a beloved English actress and comedian known for her extensive work in film, television, and theatre, particularly in British sitcoms and dramas.
-
E.
Hjördis
Hjördis is a Scandinavian feminine given name, most notably borne by Swedish model and actress Hjördis Genberg.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49aa614b48190bdc9e905e9e6d5e0 |
completed | April 19, 2026, 9:04 a.m. |
Created at: April 10, 2026, 10:18 a.m.