Triple
T36917112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virginia vs Texas Tech |
E913072
|
entity |
| Predicate | tournamentSeedTeam1 |
P88176
|
FINISHED |
| Object | South Region No. 1 seed |
—
|
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: South Region No. 1 seed | Statement: [Virginia vs Texas Tech, tournamentSeedTeam1, South Region No. 1 seed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tournamentSeedTeam1 Context triple: [Virginia vs Texas Tech, tournamentSeedTeam1, South Region No. 1 seed]
-
A.
homeTeamSeed
Indicates the ranking or seed assigned to the home team within a tournament or competition bracket.
-
B.
stateTeam1
Indicates that the first team is associated with, represents, or belongs to a particular state.
-
C.
regionTeam1
chosen
Indicates that the first team is associated with, belongs to, or represents a specific region.
-
D.
tournamentRunnerUpTeam
Indicates that a team finished in second place in a tournament, just below the champion.
-
E.
team1PreTournamentPot
Indicates the pre-tournament seeding pot or grouping to which team1 is assigned.
- 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_69f76e885b848190bad82c87e9525486 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55ad44bc8190a802bdaab36adc94 |
completed | May 6, 2026, 2:52 p.m. |
| PD | Predicate disambiguation | batch_69f7cf79ddb08190a083405cccc14137 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.