Triple
T2385822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roxy Morton |
E48819
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Gary Eggsy Unwin |
E246840
|
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: Gary Eggsy Unwin | Statement: [Roxy Morton, friend, Gary Eggsy Unwin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gary Eggsy Unwin Context triple: [Roxy Morton, friend, Gary Eggsy Unwin]
-
A.
Frank Vosper
Frank Vosper was a British actor and playwright active in the early 20th century, known for his stage work and appearances in classic British films.
-
B.
Peter Mathieson
Peter Mathieson is a British nephrologist and academic leader who has served as principal and vice-chancellor of major universities, including the University of Edinburgh and the University of Hong Kong.
-
C.
Norman Puckle
Norman Puckle is the bumbling yet well-meaning protagonist of the 1935 British comedy film "The Bulldog Breed."
-
D.
Art Eggleton
Art Eggleton is a Canadian politician who served as a long-time mayor of Toronto before later holding federal cabinet and Senate roles.
-
E.
Gary Unwin
chosen
Gary Unwin, nicknamed "Eggsy," is the street-smart protagonist and secret agent-in-training from the "Kingsman" action-spy film series.
- 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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc7d8a918819089a210e74e13be6e |
completed | March 7, 2026, 6:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aeb3ccec008190b21c0bf84f8ecd09 |
completed | March 9, 2026, 11:49 a.m. |
Created at: March 4, 2026, 7:57 p.m.