Triple
T16687710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lorna Crozier |
E405507
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Patrick Lane |
E70516
|
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: Patrick Lane | Statement: [Lorna Crozier, spouse, Patrick Lane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patrick Lane Context triple: [Lorna Crozier, spouse, Patrick Lane]
-
A.
Patrick Lane
chosen
Patrick Lane was a Canadian poet and novelist renowned for his powerful, often dark explorations of nature, memory, and personal struggle.
-
B.
Scott Lane
Scott Lane is a participant featured in the documentary series "Shots in the Dark," which follows photographers working on the overnight crime beat.
-
C.
Martin Lane
Martin Lane is a central father figure and newspaper editor on the 1960s American sitcom "The Patty Duke Show."
-
D.
Patrick Leyland
Patrick Leyland is the son of longtime Major League Baseball manager Jim Leyland and has been involved in professional baseball himself as a player and coach.
-
E.
Mike Lane
Mike Lane is the charismatic male stripper and aspiring entrepreneur portrayed by Channing Tatum in the Magic Mike 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37ea75df481909a7ebb9b2a9d0afd |
completed | April 18, 2026, 12:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a008a45af7c8190bfe09dd0e0573573 |
completed | May 10, 2026, 1:38 p.m. |
Created at: April 10, 2026, 5:19 a.m.