Triple
T303855
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American League Division Series |
E6254
|
entity |
| Predicate | tieBreakerRule |
P6631
|
FINISHED |
| Object | extra innings for tied 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: extra innings for tied games | Statement: [American League Division Series, tieBreakerRule, extra innings for tied games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tieBreakerRule Context triple: [American League Division Series, tieBreakerRule, extra innings for tied games]
-
A.
tiebreaker
chosen
Indicates that one entity serves as the deciding factor used to break a tie between two or more otherwise equal options or outcomes.
-
B.
targetScoreRule
Indicates the rule or criteria used to determine the target score to be achieved or applied in a given context.
-
C.
hasRulebook
Indicates that one entity possesses, is governed by, or is associated with a specific rulebook.
-
D.
hasDesignatedPlayerRule
Indicates that a sports league or competition uses a designated player rule allowing certain players to be treated differently for roster or salary purposes.
-
E.
playedUnderRulesOf
Indicates that an activity or game was conducted in accordance with a specified set of rules or regulations.
- 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_69a2e79230508190b912ecb555aae17e |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea2fba548190a5aeb1597dca96bd |
completed | Feb. 28, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69a2e93c367881908d3f6e2b81d44d7f |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:06 p.m.