Triple
T12043034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jigsaw |
E286710
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Mark Stevens |
E776917
|
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: Mark Stevens | Statement: [Jigsaw, editedBy, Mark Stevens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Stevens Context triple: [Jigsaw, editedBy, Mark Stevens]
-
A.
Mark Stevens
Mark Stevens was an American film and television actor best known for his roles in 1940s and 1950s dramas and film noir.
-
B.
Mark Stevens
Mark Stevens is a music producer known for his work with the artist Chaka.
-
C.
Mark Stevens
chosen
Mark Stevens is a film editor known for his work on the thriller "Phone Booth."
-
D.
Matt Strevens
Matt Strevens is a British television producer best known for his work as an executive producer on the revived era of Doctor Who.
-
E.
Don Stevens
Don Stevens is a notable individual recognized for achievements significant enough to be distinguished from others sharing the surname Stevens.
- 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_69d6ab4780948190bdb9f7620c2ac27e |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9040d13108190bd1a969fa62aae5a |
completed | April 10, 2026, 2:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f649dbf081908e76c45e362217c1 |
completed | May 2, 2026, 1:04 p.m. |
Created at: April 8, 2026, 9:47 p.m.