Triple
T19176290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NFL preseason games |
E469445
|
entity |
| Predicate | hasRuleDifferenceFrom |
P39866
|
FINISHED |
| Object | NFL regular season games |
—
|
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: NFL regular season games | Statement: [NFL preseason games, hasRuleDifferenceFrom, NFL regular season games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRuleDifferenceFrom Context triple: [NFL preseason games, hasRuleDifferenceFrom, NFL regular season games]
-
A.
hasGrammarDifferenceFrom
Indicates that two linguistic items differ from each other in their grammatical form, structure, or rules of usage.
-
B.
hasRuleDifferenceFromNFL
chosen
Indicates that the subject’s rules differ in some way from those used in the NFL.
-
C.
hasLexicalDifferencesWith
Indicates that two linguistic items differ from each other in their word choice or lexical form.
-
D.
hasDifferentVersion
Indicates that one entity exists as a version that differs in some way from another entity.
-
E.
hasRule
Indicates that an entity is governed, constrained, or defined by a specific rule or set of rules.
- 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_69d8dd09d5a081909ae43c286651ae5a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f6181f0c8190b344072db0b7abbb |
completed | April 20, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69e4b9bb158481909478ca2e06f3ba39 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:06 p.m.