Triple
T23848210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1970 National League Championship Series |
E592081
|
entity |
| Predicate | runnerUpHomeCity |
P48391
|
FINISHED |
| Object | Pittsburgh |
—
|
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: Pittsburgh | Statement: [1970 National League Championship Series, runnerUpHomeCity, Pittsburgh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runnerUpHomeCity Context triple: [1970 National League Championship Series, runnerUpHomeCity, Pittsburgh]
-
A.
runnerUpBasedIn
Indicates that an entity serving as a runner-up is located in or associated with a particular place or base of operations.
-
B.
runnerUpHomeState
Indicates the home state associated with the entity that finished in second place in a competition or ranking.
-
C.
runnerUpCountry
Indicates the country that finished in second place in a competition or ranking.
-
D.
runnerUpHomeArena
Indicates the home arena associated with the entity that finished as runner-up in a given competition or event.
-
E.
homeCityOfRunnerUpTeam
chosen
Indicates the city that serves as the home base for the team that finished in second place in a competition or event.
- 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_69e25d221d908190b9b502ad31e66a3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c9851f988190af39f57f9b71da03 |
completed | April 29, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:10 p.m.