Triple
T14054286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mechelin |
E338171
|
entity |
| Predicate | notableBearer |
P458
|
FINISHED |
| Object | Leo Mechelin |
E67239
|
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: Leo Mechelin | Statement: [Mechelin, notableBearer, Leo Mechelin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leo Mechelin Context triple: [Mechelin, notableBearer, Leo Mechelin]
-
A.
Leo Mechelin
chosen
Leo Mechelin was a Finnish statesman, liberal reformer, and professor who played a key role in Finland’s constitutional development and later helped establish Nokia as a company.
-
B.
Jean Muggli
Jean Muggli is best known as the ex-wife of former NFL star and television personality Michael Strahan and the mother of his twin daughters.
-
C.
Rodrigue Schneiter
Rodrigue Schneiter was a French engineer known for helping design the pioneering Renault FT light tank used in World War I.
-
D.
Michel Kelber
Michel Kelber was a French cinematographer known for his work on numerous European films from the 1930s through the 1970s.
-
E.
Pascal Lavanchy
Pascal Lavanchy is a French ice dancer best known for his successful competitive career in the 1990s, highlighted by multiple international medals with partner Sophie Moniotte.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de3c8d1aa48190a5055d15d9fa220c |
completed | April 14, 2026, 1:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb6608cf8819087ed5d890b82650a |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:20 p.m.