Triple
T19825062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1992 MLB All-Star Game |
E476301
|
entity |
| Predicate | managerAmericanLeague |
P64645
|
FINISHED |
| Object | Tom Kelly |
—
|
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: Tom Kelly | Statement: [1992 MLB All-Star Game, managerAmericanLeague, Tom Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Kelly Context triple: [1992 MLB All-Star Game, managerAmericanLeague, Tom Kelly]
-
A.
Tom Kelly
chosen
Tom Kelly is a former Major League Baseball manager best known for leading the Minnesota Twins to two World Series championships in 1987 and 1991.
-
B.
Tom Kelly
Tom Kelly is an American songwriter best known for co-writing numerous pop hits of the 1980s and 1990s, often in collaboration with Billy Steinberg.
-
C.
Johnny Kelly
Johnny Kelly is an American drummer best known for his long tenure with the gothic metal band Type O Negative.
-
D.
Bill Kelly
Bill Kelly is an American screenwriter best known for writing the fantasy romantic comedy film "Enchanted."
-
E.
Gene Keady
Gene Keady is a highly respected American college basketball coach best known for his long, successful tenure leading the Purdue Boilermakers.
- 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e655017c188190ae9e17ae6b0eee05 |
completed | April 20, 2026, 4:32 p.m. |
Created at: April 10, 2026, 1:50 p.m.