Triple
T9946970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ben Mears |
E195227
|
entity |
| Predicate | ally |
P4662
|
FINISHED |
| Object | Mark Petrie |
E197913
|
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 Petrie | Statement: [Ben Mears, ally, Mark Petrie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Petrie Context triple: [Ben Mears, ally, Mark Petrie]
-
A.
Mark Petrie
chosen
Mark Petrie is a courageous and resourceful young boy in Stephen King’s horror universe who becomes one of the key fighters against the vampires in ’Salem’s Lot.
-
B.
Stephen Peters
Stephen Peters is an American screenwriter best known for writing the neo-noir thriller film "Wild Things."
-
C.
Tim McClelland
Tim McClelland is a former Major League Baseball umpire known for his long tenure, distinctive strike zone, and involvement in several high-profile postseason games.
-
D.
Michael Potts
Michael Potts is an American actor known for his work in film, television, and theater, including notable roles in projects like "The Wire," "True Detective," and various Broadway productions.
-
E.
Michael Pryor
Michael Pryor is an American entrepreneur and software executive best known as the co-founder and longtime leader of the project management platform Trello.
- 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_69ca82e96a108190932bd1fc4acd73a0 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb657b35c81909448e93999f6e77c |
completed | April 2, 2026, 12:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2292257bc8190b3a15de60d7c9ba2 |
completed | April 5, 2026, 9:19 a.m. |
Created at: March 30, 2026, 8:45 p.m.