Triple
T26295015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shawn Bradley |
E661389
|
entity |
| Predicate | teamCityPlayedFor |
P22309
|
FINISHED |
| Object | Philadelphia |
—
|
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: Philadelphia | Statement: [Shawn Bradley, teamCityPlayedFor, Philadelphia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamCityPlayedFor Context triple: [Shawn Bradley, teamCityPlayedFor, Philadelphia]
-
A.
playedForCity
chosen
Indicates that an entity (typically a person or team) has been a member of or represented a sports team or organization based in a particular city.
-
B.
homeCityTeamOf
Indicates that one entity is the sports team based in and representing the home city of the other entity.
-
C.
teamCityCoached
Indicates that a particular coach is responsible for coaching a specific sports team based in a given 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.
team2FormerCity
Indicates that a team was previously based in, or associated with, a particular city in the past.
- 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_69ee812cd48c81908054068f545f0526 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f638d11c988190af7fd4572b08e038 |
completed | May 2, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69f63706b6008190993577193c85ff50 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 26, 2026, 10:11 p.m.