Triple
T31110410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Nexus |
E792927
|
entity |
| Predicate | firstMajorAngle |
P204304
|
FINISHED |
| Object | attack on John Cena |
—
|
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: attack on John Cena | Statement: [The Nexus, firstMajorAngle, attack on John Cena]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstMajorAngle Context triple: [The Nexus, firstMajorAngle, attack on John Cena]
-
A.
firstMajorRoute
Indicates that the specified route is the primary or earliest major route associated with an entity (such as a location, project, or network).
-
B.
firstDropAngle
Indicates the angle at which an object or entity initially begins to fall or be dropped from its starting position.
-
C.
firstMajorDescription
Indicates that the object is the primary or earliest major field of study associated with the subject.
-
D.
firstMajorDevelopment
Indicates that the object is the earliest significant development, milestone, or major advancement associated with the subject.
-
E.
firstMajorVersionBy
Indicates that one entity is the earliest or initial major version created or released by another entity.
- 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_69f224cfd5d881908ec6447bc321cd58 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a0379a4086c8190a83df5570f737e15 |
completed | May 12, 2026, 7:04 p.m. |
| PD | Predicate disambiguation | batch_6a037049db848190a6268bf1a8a60223 |
completed | May 12, 2026, 6:24 p.m. |
| PDg | Predicate description generation | batch_6a0379a33dc48190a29f72268c8ca8a8 |
completed | May 12, 2026, 7:04 p.m. |
Created at: April 29, 2026, 9:04 p.m.