Triple
T22708763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Safety In Numbers |
E561533
|
entity |
| Predicate | mainPerformer |
P1363
|
FINISHED |
| Object | Kris Myers |
—
|
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: Kris Myers | Statement: [Safety In Numbers, mainPerformer, Kris Myers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kris Myers Context triple: [Safety In Numbers, mainPerformer, Kris Myers]
-
A.
Kris Myers
chosen
Kris Myers is an American drummer best known for his long-time role as the percussionist for the progressive rock and jam band Umphrey's McGee.
-
B.
Kevin Myers
Kevin Myers is an individual known primarily in relation to Vicky Lathum as her friend, with no widely documented public profile.
-
C.
Kevin Myers
Kevin Myers is a central character in the American Pie film series, known as one of the core group of friends navigating relationships and adulthood.
-
D.
Kris Hitchen
Kris Hitchen is a British actor best known for his lead role in Ken Loach’s social-realist drama "Sorry We Missed You."
-
E.
Kris McQuade
Kris McQuade is an Australian actress known for her extensive work in film, television, and theatre since the 1970s.
- 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_69e2454f1348819088d83f420925a5c1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f178d11d4081909981872698b6c45e |
completed | April 29, 2026, 3:19 a.m. |
Created at: April 17, 2026, 3:17 p.m.