Triple
T10908565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Merkur Scorpio |
E257632
|
entity |
| Predicate | manufacturer |
P490
|
FINISHED |
| Object | Merkur |
E8610
|
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: Merkur | Statement: [Merkur Scorpio, manufacturer, Merkur]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Merkur Context triple: [Merkur Scorpio, manufacturer, Merkur]
-
A.
Merkur
chosen
Merkur was a short-lived automotive marque created by Ford in the 1980s to sell European-designed performance and luxury cars in the North American market.
-
B.
Mercuri
Mercuri is the surname of Brazilian singer, songwriter, and performer Daniela Mercury, a prominent figure in axé and pop music.
-
C.
Mercury
Mercury was an American automobile marque of the Ford Motor Company known for producing mid-priced cars positioned between Ford and Lincoln.
-
D.
Mercury
Mercury is the Roman god of commerce, communication, and travel, often depicted as a swift messenger of the gods.
-
E.
Mercury
Mercury is the nickname of former American football running back Eugene "Mercury" Morris, best known for his role on the undefeated 1972 Miami Dolphins team.
- 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_69d6aa8550c8819095508a2ed9acf3db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7706824d08190ba894d144cc6b3ba |
completed | April 9, 2026, 9:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e23baecb008190b74bcbad1db61a91 |
completed | April 17, 2026, 1:54 p.m. |
Created at: April 8, 2026, 9:22 p.m.