Triple
T7325985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBA blocks leader |
E168875
|
entity |
| Predicate | secondaryStatUnit |
P49001
|
FINISHED |
| Object | total blocks |
—
|
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: total blocks | Statement: [NBA blocks leader, secondaryStatUnit, total blocks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryStatUnit Context triple: [NBA blocks leader, secondaryStatUnit, total blocks]
-
A.
secondaryMetric
Indicates that one metric serves as an additional, supporting measure used alongside a primary metric for evaluation or analysis.
-
B.
statisticalUnitOf
chosen
Indicates that one entity serves as the statistical unit (the basic unit of observation or analysis) for which data or statistics are collected or reported about another entity.
-
C.
secondaryState
Indicates that an entity is in a subordinate or less primary condition, status, or mode relative to its main or primary state.
-
D.
secondaryOutcome
Indicates that an outcome occurs as a secondary, subordinate, or additional result relative to a primary outcome.
-
E.
secondaryTo
Indicates that one condition, event, or factor occurs as a consequence of, or is caused by, another primary condition, event, or factor.
- 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_69c68a54cacc81908e3b773441f19566 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f0a612c08190b7a3fefa811bbcec |
completed | March 27, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69c6e77230048190b2c29ca6b3a65b8e |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3:03 p.m.