Triple
T17320835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bobby Thomson |
E420554
|
entity |
| Predicate | homeRunDescription |
P46257
|
FINISHED |
| Object | pennant-winning three-run homer off Ralph Branca |
—
|
LITERAL 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: pennant-winning three-run homer off Ralph Branca | Statement: [Bobby Thomson, homeRunDescription, pennant-winning three-run homer off Ralph Branca]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeRunDescription Context triple: [Bobby Thomson, homeRunDescription, pennant-winning three-run homer off Ralph Branca]
-
A.
homeRunDefinition
Indicates that an event or action qualifies as a home run according to the rules or criteria of the relevant sport or context.
-
B.
homeRunType
chosen
Indicates the specific kind of home run that was hit in a baseball play (e.g., solo, two-run, three-run, grand slam).
-
C.
homeRunInteraction
Indicates an interaction where a batter successfully hits a home run, establishing the event and its participants.
-
D.
homeRunTitle
Indicates that one entity is the title or name given to a home run event associated with another entity.
-
E.
homeRunHittingAbility
Indicates the capability or skill level of an entity to hit home runs.
- F. None of above.
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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439cf5394819089bff5f8dc2e8241 |
completed | April 19, 2026, 2:11 a.m. |
| PD | Predicate disambiguation | batch_69e3b01b9d1c8190a406dd941c9b11a1 |
completed | April 18, 2026, 4:23 p.m. |
Created at: April 10, 2026, 5:43 a.m.