Triple
T28192446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2021 NBA Finals |
E716352
|
entity |
| Predicate | yearsSincePreviousTitle |
P164113
|
FINISHED |
| Object | 50 |
—
|
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: 50 | Statement: [2021 NBA Finals, yearsSincePreviousTitle, 50]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearsSincePreviousTitle Context triple: [2021 NBA Finals, yearsSincePreviousTitle, 50]
-
A.
runnerUpPreviousTitleCount
Indicates the number of times an entity has previously finished as runner-up in a given competition or title context.
-
B.
hasHadInterimTitles
Indicates that an entity has previously held one or more temporary or provisional titles before obtaining a permanent or final title.
-
C.
yearsSincePreviousSoloSingle
Indicates the number of years that have passed between an entity’s current solo single and their immediately preceding solo single.
-
D.
numberOfTimesTitleHeld
Indicates how many separate times a particular title or position has been held by an entity.
-
E.
runnerUpPreviousTitleYear
Indicates that an entity was the runner-up for a specific title in the immediately preceding year.
- F. None of above. chosen
Provenance (4 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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f642ce9aec8190bb3e76ca66824af7 |
completed | May 2, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69f63c6c1a948190b68c0f92c264cc0c |
completed | May 2, 2026, 6:03 p.m. |
| PDg | Predicate description generation | batch_69f63fd4f7448190930c723ba7cfce62 |
completed | May 2, 2026, 6:17 p.m. |
Created at: April 27, 2026, 10:26 p.m.