Triple
T1351442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mike Lowell |
E28890
|
entity |
| Predicate | runsBattedInCareerApprox |
P7537
|
FINISHED |
| Object | 952 |
—
|
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: 952 | Statement: [Mike Lowell, runsBattedInCareerApprox, 952]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runsBattedInCareerApprox Context triple: [Mike Lowell, runsBattedInCareerApprox, 952]
-
A.
careerRBIs
chosen
Indicates the total number of runs a player has batted in over the course of their entire career.
-
B.
careerRunsScored
Indicates the total number of runs an entity has scored over the entire duration of their playing career.
-
C.
clinchingHomeRunRunsBattedIn
Indicates that a particular home run both clinches a game or series and accounts for specific runs batted in (RBIs) scored by the batter.
-
D.
onBasePlusSluggingCareer
Indicates a player’s career-long combined performance in getting on base and hitting for power, typically measured as on-base percentage plus slugging percentage.
-
E.
careerStolenBases
Indicates the total number of bases a player successfully stole over the entire span of their playing career.
- 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_69a498571d248190a0ac9eb02d97097f |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c26b1b4881908ae4b1b2c9b268a0 |
completed | March 1, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69a4bef5857c81909ae984feb85a26ca |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:56 p.m.