Triple
T514960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MLB All-Star Game |
E10685
|
entity |
| Predicate | rosterSize |
P15427
|
FINISHED |
| Object | expanded compared to 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: expanded compared to regular-season games | Statement: [MLB All-Star Game, rosterSize, expanded compared to regular-season games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rosterSize Context triple: [MLB All-Star Game, rosterSize, expanded compared to regular-season games]
-
A.
rosterSizeRegularSeason
Indicates the number of players a team is allowed or has on its roster during the regular season.
-
B.
teamRosterLimit
Indicates the maximum number of members that are allowed to be on a team’s roster.
-
C.
typicalTeamSize
Indicates the usual or most common number of members that make up a given team.
-
D.
teamCountType
Indicates how the number of teams is categorized or measured within a given context.
-
E.
typicalRosterSource
Indicates that one entity is the usual or standard source from which the other entity’s roster or list of members is derived.
- 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_69a2e84a0d08819087e01863fcd9abf1 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f232fa688190b08a2fe3f22c7a6e |
completed | Feb. 28, 2026, 1:48 p.m. |
| PD | Predicate disambiguation | batch_69a2f013c05481909e6dc87e7b20ebd8 |
completed | Feb. 28, 2026, 1:39 p.m. |
| PDg | Predicate description generation | batch_69a2f23214248190aa5fe1138f0f5a58 |
completed | Feb. 28, 2026, 1:48 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.