Triple
T37544504
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rex Ryan’s 3–4 attacking defense |
E933419
|
entity |
| Predicate | notableUsageTeam |
P189356
|
FINISHED |
| Object | Baltimore Ravens |
E12083
|
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: Baltimore Ravens | Statement: [Rex Ryan’s 3–4 attacking defense, notableUsageTeam, Baltimore Ravens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableUsageTeam Context triple: [Rex Ryan’s 3–4 attacking defense, notableUsageTeam, Baltimore Ravens]
-
A.
usedByTeams
chosen
Indicates that something (such as a tool, resource, or process) is utilized or employed by one or more teams.
-
B.
notableTeamType
Indicates that an entity is notably associated with a team of a specified type (e.g., national team, club team, or other team category).
-
C.
notableTeams
Indicates that there is a noteworthy association between an entity and one or more teams with which it is significantly connected or recognized.
-
D.
notableTeamOperated
Indicates that an entity is or was operated, managed, or run by a team that is considered notable or significant.
-
E.
notableRecipientTeam
Indicates that an entity has received a notable award, honor, or recognition specifically in the context of a particular 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_69f76eca55bc8190acf25741793d5dac |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a409f0a305881908d60869be6f819ff |
completed | June 28, 2026, 4:11 a.m. |
| PD | Predicate disambiguation | batch_6a037a1553e08190bb7424c448cb1f33 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:17 p.m.