Triple
T36841773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miami Miracle |
E910426
|
entity |
| Predicate | notableOpponentPlayerOnField |
P103928
|
FINISHED |
| Object | Rob Gronkowski |
E978
|
NE 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: Rob Gronkowski | Statement: [Miami Miracle, notableOpponentPlayerOnField, Rob Gronkowski]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableOpponentPlayerOnField Context triple: [Miami Miracle, notableOpponentPlayerOnField, Rob Gronkowski]
-
A.
notableRivalOpponent
Indicates that one entity is a particularly significant or well-known rival or opponent of another entity.
-
B.
notableOpponentTeamMember
chosen
Indicates that a specific team member is recognized as a particularly significant or noteworthy opponent in relation to another entity or context.
-
C.
hasNotablePlayer
Indicates that an entity (such as a team or club) is associated with a player who is particularly distinguished, famous, or significant in its context.
-
D.
notableTeammate
Indicates that one entity has a teammate relationship with another entity who is particularly prominent, distinguished, or noteworthy.
-
E.
notableRivalTeam
Indicates that one team is recognized as a significant or well-known rival of another team.
- F. None of above.
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_69f76e7f65a881908651b702da592b6d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3dde74418881908431623e65ff4f44 |
completed | June 26, 2026, 2:05 a.m. |
| PD | Predicate disambiguation | batch_6a037a0e039481908a4a2666f76c5363 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:13 p.m.