Triple
T11985439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sparky |
E285264
|
entity |
| Predicate | setting |
P1957
|
FINISHED |
| Object | New Holland |
E285263
|
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: New Holland | Statement: [Sparky, setting, New Holland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: New Holland Context triple: [Sparky, setting, New Holland]
-
A.
New Holland
New Holland was the name given by the Dutch to their 17th-century colonial possessions in northeastern Brazil, known historically as Dutch Brazil.
-
B.
New Holland
chosen
New Holland is the fictional, retro-styled American suburb that serves as the primary setting for Tim Burton’s animated film "Frankenweenie."
-
C.
Claas
Claas is a given name and surname of Germanic origin, used as a variant of names like Claes or Klaus.
-
D.
Steyr Tractor
Steyr Tractor is an Austrian agricultural machinery brand known for producing high-quality tractors, historically linked to the former industrial conglomerate Steyr-Daimler-Puch.
-
E.
Massey-Ferguson
Massey-Ferguson is a major agricultural machinery manufacturer best known for its tractors and farm equipment used worldwide.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903acbb9081908fe7f8360057785c |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f47237c23081909044388ff5dc73b3 |
completed | May 1, 2026, 9:28 a.m. |
Created at: April 8, 2026, 9:46 p.m.