Triple
T11559082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Memphis Southmen |
E274088
|
entity |
| Predicate | notablePlayer |
P304
|
FINISHED |
| Object | Jim Kiick |
E882904
|
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: Jim Kiick | Statement: [Memphis Southmen, notablePlayer, Jim Kiick]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jim Kiick Context triple: [Memphis Southmen, notablePlayer, Jim Kiick]
-
A.
Jim Kiick
chosen
Jim Kiick was an American running back best known as a key member of the Miami Dolphins’ dominant early-1970s teams, including their perfect 1972 season.
-
B.
Mark Kamine
Mark Kamine is a film and television producer known for his work on projects such as the comedy film "Bad Moms."
-
C.
Mike Cowling
Mike Cowling is an athlete known for playing for the sports team The Warriors.
-
D.
Tom Kellogg
Tom Kellogg was an American industrial designer best known for his influential work on innovative automobile designs in the mid-20th century.
-
E.
Tom Johnson
Tom Johnson is an American former professional boxer and long-reigning IBF featherweight champion known for his title defenses in the 1990s.
- 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_69d6aae4dfa48190a3ab0b19a159a3c5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88a888e8481909386009b9603e4d3 |
completed | April 10, 2026, 5:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e713a7e16481908faabcafe11daf37 |
completed | April 21, 2026, 6:05 a.m. |
Created at: April 8, 2026, 9:37 p.m.