Triple
T23955115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savannah Sand Gnats |
E603765
|
entity |
| Predicate | predecessorFranchiseInCity |
P27015
|
FINISHED |
| Object | Savannah Cardinals |
—
|
NE NERFINISHED |
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: Savannah Cardinals | Statement: [Savannah Sand Gnats, predecessorFranchiseInCity, Savannah Cardinals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorFranchiseInCity Context triple: [Savannah Sand Gnats, predecessorFranchiseInCity, Savannah Cardinals]
-
A.
predecessorFranchise
Indicates that one franchise directly precedes and is succeeded by another franchise in a series or lineage.
-
B.
predecessorLeagueInCity
Indicates that one sports league previously operated in a given city before another league took its place there.
-
C.
previousFranchiseCity
Indicates that a city was formerly the home location of a particular franchise before it moved or relocated.
-
D.
teamPredecessorCity
chosen
Indicates that one sports team previously based in a given city is the predecessor or earlier incarnation of another team in that city.
-
E.
previousFranchiseName
Indicates that an entity previously operated under a different franchise name, specifying what that earlier franchise name was.
- 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_69e2954222288190a7323554d0cca8d7 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d0d616ec81908c796894f40f3015 |
completed | April 29, 2026, 9:35 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:21 p.m.