Triple
T49677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Kraft |
E976
|
entity |
| Predicate | acquiredSportsTeam |
P2617
|
FINISHED |
| Object | New England Patriots in 1994 |
—
|
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: New England Patriots in 1994 | Statement: [Robert Kraft, acquiredSportsTeam, New England Patriots in 1994]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: acquiredSportsTeam Context triple: [Robert Kraft, acquiredSportsTeam, New England Patriots in 1994]
-
A.
hasSportsTeam
Indicates that an entity possesses, sponsors, or is represented by a sports team.
-
B.
hasMajorSportsTeam
Indicates that a location is home to at least one prominent, officially recognized sports team, typically in a major professional or collegiate league.
-
C.
containsSportsTeam
Indicates that one entity (typically a location or organization) has a sports team as part of it or within its boundaries.
-
D.
league
Indicates that an organization or team participates in, is a member of, or is associated with a particular sports or competitive league.
-
E.
affiliateLeague
Indicates that one sports organization or team is formally associated with and operates under the umbrella or partnership of a particular league.
- 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24b6c9eb88190b2fe85e427f4177a |
completed | Feb. 28, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_69a24ac0fb088190b7a5e87817e8e747 |
completed | Feb. 28, 2026, 1:54 a.m. |
| PDg | Predicate description generation | batch_69a24b6b7638819095a86e2151635a02 |
completed | Feb. 28, 2026, 1:56 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.