Triple
T20944910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orlando Thunder |
E515818
|
entity |
| Predicate | homeCityTeamRelationship |
P5864
|
FINISHED |
| Object | based in Orlando, Florida |
—
|
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: based in Orlando, Florida | Statement: [Orlando Thunder, homeCityTeamRelationship, based in Orlando, Florida]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeCityTeamRelationship Context triple: [Orlando Thunder, homeCityTeamRelationship, based in Orlando, Florida]
-
A.
homeCityTeamOf
Indicates that one entity is the sports team based in and representing the home city of the other entity.
-
B.
homeCityOfRivalTeam
Indicates the city that serves as the home base for a team’s rival.
-
C.
homeCityTeamStatus
Indicates the relationship between a team and a city specifying that the team is considered the home or primary representative team of that city.
-
D.
teamCityOfFranchiseOwned
Indicates that a particular city serves as the home or base city for a sports franchise that is owned by a specified owner.
-
E.
hasHomeCity
chosen
Indicates that an entity’s primary or official city of residence or affiliation is a specified city.
- 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_69e0b4fc13408190b06868df03c5c29b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fad705e481909da0098d7c73cd02 |
completed | April 21, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69e5c9b1bae48190a845165fed1b005e |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:55 p.m.