Triple
T21812105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George MacDonald Fraser |
E538500
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Fraser |
—
|
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: Fraser | Statement: [George MacDonald Fraser, familyName, Fraser]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fraser Context triple: [George MacDonald Fraser, familyName, Fraser]
-
A.
Fraser
chosen
Fraser is a common Scottish surname historically associated with the Clan Fraser and borne by many notable figures worldwide.
-
B.
Fraser
Fraser is a small mountain town in Colorado known for its proximity to ski resorts and outdoor recreation in the Rocky Mountains.
-
C.
Fraser
Fraser is a residential suburb in the Belconnen district of Canberra, in the Australian Capital Territory.
-
D.
Freser
Freser is a river in Catalonia, Spain, known for flowing through the Pyrenees and joining the Ter River.
-
E.
Fraser James
Fraser James is a British actor known for his work in film, television, and web series, including a starring role in the sci-fi web series "Origin."
- 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_69e0c473f0f8819086c9d1b4a143bd67 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f07cc6cdf88190a31129acdc3bcec8 |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 16, 2026, 6:53 p.m.