Triple
T20344390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tyco BMW |
E495826
|
entity |
| Predicate | sponsors |
P1807
|
FINISHED |
| Object | Tyco |
—
|
NE NERFINISHED |
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: Tyco | Statement: [Tyco BMW, sponsors, Tyco]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tyco Context triple: [Tyco BMW, sponsors, Tyco]
-
A.
Tyco International
chosen
Tyco International was a multinational conglomerate known for its security systems, fire protection, and industrial products before being acquired by Johnson Controls.
-
B.
Honeywell
Honeywell is a multinational conglomerate best known for its aerospace systems, building technologies, performance materials, and industrial automation products.
-
C.
Fortive
Fortive is an American diversified industrial technology company that owns and operates a portfolio of measurement, automation, and industrial solutions businesses.
-
D.
Guardian Industries
Guardian Industries is a major global manufacturer of glass, automotive, and building products, known for its architectural and float glass operations.
-
E.
Mitre Corporation
Mitre Corporation is a not-for-profit organization that operates federally funded research and development centers, providing systems engineering and advanced technology support primarily to U.S. government agencies.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67837bef8819091e552d1c8a1665c |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:24 a.m.