Triple
T1279922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Thomas |
E27299
|
entity |
| Predicate | BattingAverage |
P14861
|
FINISHED |
| Object | .301 |
—
|
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: .301 | Statement: [Frank Thomas, BattingAverage, .301]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: BattingAverage Context triple: [Frank Thomas, BattingAverage, .301]
-
A.
battingAverage
chosen
Indicates the statistical relationship between a batter’s number of hits and official at-bats, expressing how often they successfully get a hit.
-
B.
careerBattingAverage
Indicates the long-term batting performance of a player, calculated as their total hits divided by total at-bats over their entire career.
-
C.
ledLeagueInBattingAverage
Indicates that an entity achieved the highest batting average in a particular league over a specified season or time period.
-
D.
onBasePlusSlugging
Indicates a relationship where a player’s offensive performance is quantified by combining their on-base percentage with their slugging percentage into a single metric.
-
E.
homeRunRate
Indicates the frequency at which a player or team hits home runs relative to a specified number of opportunities (such as at-bats, plate appearances, or games).
- 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_69a496d3710c8190955dee8bc0dacb50 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c092eb688190bf42bbd59e4ff289 |
completed | March 1, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69a4bee276d8819092f71c5a1140bb61 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:50 p.m.