Triple
T8318572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dunkin' |
E194768
|
entity |
| Predicate | competitor |
P1375
|
FINISHED |
| Object | Tim Hortons |
E154795
|
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: Tim Hortons | Statement: [Dunkin', competitor, Tim Hortons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tim Hortons Context triple: [Dunkin', competitor, Tim Hortons]
-
A.
Tim Hortons
chosen
Tim Hortons is a Canadian multinational fast-food restaurant chain best known for its coffee, doughnuts, and baked goods.
-
B.
Tim Horton
Tim Horton was a Canadian professional ice hockey defenceman and co-founder of the Tim Hortons coffee and doughnut restaurant chain.
-
C.
Starbuck
Starbuck is the morally conscientious first mate of the whaling ship Pequod in Herman Melville’s novel "Moby-Dick," serving as a cautious and ethical counterpoint to Captain Ahab’s obsessive quest.
-
D.
Austin Stack
Austin Stack was an Irish revolutionary and politician who played a leading role in the struggle for independence and later opposed the Anglo-Irish Treaty.
-
E.
William Lundigan
William Lundigan was an American film and television actor active from the 1930s through the 1960s, known for roles in dramas, war films, and early TV 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_69ca82e6e2648190a31eaf6f4f757b2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7f648e10819081ad1fed870b2b86 |
completed | March 31, 2026, 8:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd9596891c81909296050d0a8117ca |
completed | April 1, 2026, 10 p.m. |
Created at: March 30, 2026, 5:55 p.m.