Triple
T3730325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ted Williams |
E79044
|
entity |
| Predicate | onBasePercentageRecord |
P26689
|
FINISHED |
| Object | highest career OBP in MLB history |
—
|
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: highest career OBP in MLB history | Statement: [Ted Williams, onBasePercentageRecord, highest career OBP in MLB history]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onBasePercentageRecord Context triple: [Ted Williams, onBasePercentageRecord, highest career OBP in MLB history]
-
A.
OnBasePercentage
chosen
Indicates the frequency with which a batter successfully reaches base (by hit, walk, or hit-by-pitch) per plate appearance.
-
B.
creditPercentage
Indicates the proportion or share of credit assigned to an entity in relation to a particular outcome, contribution, or transaction.
-
C.
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.
-
D.
calculationBasis
Indicates the rule, method, or reference standard used as the foundation for performing a calculation in the relationship.
-
E.
baselineType
Indicates the type or category of a baseline used as a reference point for comparison or evaluation.
- 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_69ad8b0e4650819090ad7cef094285e8 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb1bb5408190990ea4dfbdab5c68 |
completed | March 8, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69adc04746588190b0dc535638f23546 |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.