Triple
T35284292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Fish That Saved Pittsburgh |
E1019032
|
entity |
| Predicate | fictionalTeamName |
P198771
|
FINISHED |
| Object | Pittsburgh Pythons |
—
|
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 Pythons | Statement: [The Fish That Saved Pittsburgh, fictionalTeamName, Pittsburgh Pythons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fictionalTeamName Context triple: [The Fish That Saved Pittsburgh, fictionalTeamName, Pittsburgh Pythons]
-
A.
fictionalTeam
Indicates that the related entities are members of, or otherwise associated with, the same fictional team within a narrative or imaginary context.
-
B.
fictionalTeamManaged
Indicates that one entity is responsible for managing or overseeing the operations, activities, or direction of a fictional team.
-
C.
championTeamFullName
Indicates the full official name of the team that won a championship or competition.
-
D.
formerSportsTeam
Indicates that an entity was once a member of or played for a particular sports team in the past but no longer does so.
-
E.
teamName
Indicates the relationship that assigns or associates a specific name with a particular team.
- F. None of above. chosen
Provenance (4 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_69f76de6d39c8190bb11342e4b91ff2b |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff0491409c8190be40f633a58da0b1 |
completed | May 9, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69ff040bb5cc81909534c7eee85d5e90 |
completed | May 9, 2026, 9:53 a.m. |
| PDg | Predicate description generation | batch_69ff04901ab081908b68563836fcdc99 |
completed | May 9, 2026, 9:55 a.m. |
Created at: May 3, 2026, 4:03 p.m.