Triple
T17173777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mars, Incorporated |
E416803
|
entity |
| Predicate | notableProduct |
P1448
|
FINISHED |
| Object | Mars bar |
E1253397
|
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: Mars bar | Statement: [Mars, Incorporated, notableProduct, Mars bar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mars bar Context triple: [Mars, Incorporated, notableProduct, Mars bar]
-
A.
Mars bar
chosen
Mars bar is a popular chocolate candy bar consisting of nougat and caramel covered in milk chocolate, sold internationally under the Mars brand.
-
B.
Snickers
Snickers is a character in the Australian animated children's series "Bluey," known as a dachshund pup who is one of Bluey's friends.
-
C.
Snickers
Snickers is a popular chocolate bar made of nougat, caramel, and peanuts covered in milk chocolate, produced and marketed worldwide.
-
D.
Oreo
Oreo is a popular chocolate sandwich cookie with a sweet cream filling, widely recognized as one of the best-selling and most iconic cookie brands in the world.
-
E.
M&M's
M&M's are colorful button-shaped chocolate candies with a hard sugar shell, famous for their “melts in your mouth, not in your hand” slogan and wide variety of flavors.
- 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_69d886d5f34c8190b24564dfaa63f3fb |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3fc0b7c9c819082e503cb493d7e7b |
completed | April 18, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a015fc83984819098c98b75cf021e3a |
completed | May 11, 2026, 4:49 a.m. |
Created at: April 10, 2026, 5:37 a.m.