Triple
T21364361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edith Lyons |
E526869
|
entity |
| Predicate | hasRelative |
P367
|
FINISHED |
| Object | Stephen Lyons |
E1126416
|
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: Stephen Lyons | Statement: [Edith Lyons, hasRelative, Stephen Lyons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stephen Lyons Context triple: [Edith Lyons, hasRelative, Stephen Lyons]
-
A.
Stephen Lyons
Stephen Lyons is a central character in the British drama series "Years and Years," which follows a Manchester family navigating rapid social and political changes over several decades.
-
B.
Stephen Lyons
chosen
Stephen Lyons is a person known primarily as a family member of Daniel Lyons.
-
C.
James Lyons
James Lyons was an American film editor and occasional screenwriter best known for his frequent collaborations with director Todd Haynes on acclaimed independent films.
-
D.
Michael Lyons
Michael Lyons is a British public servant and former chairman of the BBC Trust, known for his leadership roles in local government and public sector organizations.
-
E.
Eric Lyons
Eric Lyons is a technology entrepreneur best known as a co-founder of the software company Altamira Software.
- 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_69e0b51d8a308190b09113b3b3f9bc15 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b06d6dcc8190b438d3c2e620578c |
completed | April 22, 2026, 11:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09cfde40a08190a577e3999c1836ce |
completed | May 17, 2026, 2:25 p.m. |
Created at: April 16, 2026, 5:08 p.m.