Triple
T14999521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Cancro |
E374046
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Jersey Mike’s Subs |
E76535
|
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: Jersey Mike’s Subs | Statement: [Peter Cancro, employer, Jersey Mike’s Subs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jersey Mike’s Subs Context triple: [Peter Cancro, employer, Jersey Mike’s Subs]
-
A.
Jersey Mike’s Subs
chosen
Jersey Mike’s Subs is an American fast-casual sandwich chain known for its freshly sliced subs and cheesesteaks made to order.
-
B.
Jimmy John’s
Jimmy John’s is an American sandwich restaurant chain known for its fast service and customizable submarine sandwiches.
-
C.
IND Subway
IND Subway is the city-owned Independent Subway System in New York City, built in the early 20th century to compete with private transit operators and now forming a core part of the modern NYC Subway.
-
D.
Panera Bread
Panera Bread is a popular American fast-casual restaurant and bakery chain known for its soups, salads, sandwiches, and freshly baked bread.
-
E.
Papa Murphy's
Papa Murphy's is a take-and-bake pizza chain where customers purchase uncooked pizzas to bake at home.
- 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_69d85ccc84388190aa151e5173370c8d |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded71a5618819083ae96a79735ef98 |
completed | April 15, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9dcbd7c88190ad1a302cd0c6ef28 |
completed | May 9, 2026, 2:37 a.m. |
Created at: April 10, 2026, 2:54 a.m.