Triple
T19002784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ross Miner |
E464997
|
entity |
| Predicate | formerCoach |
P4378
|
FINISHED |
| Object | Peter Johansson |
—
|
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: Peter Johansson | Statement: [Ross Miner, formerCoach, Peter Johansson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Johansson Context triple: [Ross Miner, formerCoach, Peter Johansson]
-
A.
Peter Johansson
chosen
Peter Johansson is a figure skating coach known for training elite skaters such as Emily Hughes.
-
B.
Olof Lagercrantz
Olof Lagercrantz was a prominent Swedish literary critic, writer, and newspaper editor known for his influential essays and biographies.
-
C.
Erik Palmstedt
Erik Palmstedt was an 18th-century Swedish architect best known for his influential neoclassical designs in Stockholm.
-
D.
Charles Boberg
Charles Boberg is a linguist and scholar of North American English dialects, particularly known for his work on regional variation and phonology.
-
E.
Anders Lundin
Anders Lundin is a Swedish television presenter, comedian, and musician best known for hosting popular entertainment shows in Sweden.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6a252588190a40398b1879fb096 |
completed | April 20, 2026, 7:32 a.m. |
Created at: April 10, 2026, 12:01 p.m.