Triple
T16306467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Five Legs |
E395927
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Graeme Gibson |
E91849
|
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: Graeme Gibson | Statement: [Five Legs, author, Graeme Gibson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Graeme Gibson Context triple: [Five Legs, author, Graeme Gibson]
-
A.
Graeme Gibson
chosen
Graeme Gibson was a Canadian novelist, environmentalist, and cultural advocate known for his contributions to Canadian literature and his long partnership with writer Margaret Atwood.
-
B.
Graeme Lorimer
Graeme Lorimer is known primarily as the son of American journalist and long-time Saturday Evening Post editor George Horace Lorimer.
-
C.
Graeme Ferguson
Graeme Ferguson was a Canadian filmmaker and co-founder of the IMAX large-format cinema technology.
-
D.
Colin Milne
Colin Milne was an 18th–19th century Scottish clergyman and botanist known for his works on natural history and religious subjects.
-
E.
Graeme McDonald
Graeme McDonald is a television producer known for his work on the British series "Meantime."
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e288d5619081909d0f8157cc487877 |
completed | April 17, 2026, 7:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a008a2156008190a079c9f1b721d40a |
completed | May 10, 2026, 1:37 p.m. |
Created at: April 10, 2026, 5:06 a.m.