Triple
T17610082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sir John Lyons |
E428943
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | John Lyons |
—
|
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: John Lyons | Statement: [Sir John Lyons, name, John Lyons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Lyons Context triple: [Sir John Lyons, name, John Lyons]
-
A.
John Lyons
John Lyons is a film producer best known for his work on major Hollywood comedies, including the Austin Powers series.
-
B.
John Lyons
chosen
John Lyons was a prominent British linguist and semanticist known for his influential work on theoretical linguistics and the philosophy of language.
-
C.
John Loughlin
John Loughlin was the first Roman Catholic bishop of the Diocese of Brooklyn, serving from its establishment in the mid-19th century and overseeing its early growth.
-
D.
Douglas Guilfoyle
Douglas Guilfoyle is an international law scholar known for his work on the law of the sea, maritime security, and international criminal law.
-
E.
Christopher Smyth
Christopher Smyth was one of the mountaineers who achieved the first recorded ascent of Dufourspitze, the highest peak in Switzerland and the Monte Rosa massif.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46d2d294881908380b2ab0b4d2503 |
completed | April 19, 2026, 5:50 a.m. |
Created at: April 10, 2026, 5:51 a.m.