Triple
T4486488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GM2900 platform |
E107251
|
entity |
| Predicate | usedByBrand |
P23474
|
FINISHED |
| Object | Daewoo |
E432266
|
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: Daewoo | Statement: [GM2900 platform, usedByBrand, Daewoo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daewoo Context triple: [GM2900 platform, usedByBrand, Daewoo]
-
A.
Daewoo
chosen
Daewoo is a South Korean automotive brand known for producing a range of affordable passenger vehicles and later becoming part of General Motors' global operations.
-
B.
LG Electronics
LG Electronics is a South Korean multinational electronics company known for producing a wide range of consumer electronics, home appliances, and mobile devices.
-
C.
Sanyo
Sanyo is a Japanese electronics brand known for producing a wide range of consumer and industrial electronic products, including televisions, batteries, and home appliances.
-
D.
LG Corporation
LG Corporation is a major South Korean multinational conglomerate with diversified businesses spanning electronics, chemicals, and telecommunications.
-
E.
GM Daewoo
GM Daewoo was a South Korean automobile manufacturer and former subsidiary of General Motors, known for producing a range of compact and mid-size cars for global markets.
- 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_69bd43f84f788190a1383579c4a595be |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd52a958288190974b292f54a0e045 |
completed | March 20, 2026, 1:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bd679cd3b88190a9b90f50f2b7beae |
completed | March 20, 2026, 3:28 p.m. |
Created at: March 20, 2026, 12:59 p.m.