Triple
T10070720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matt Hughes |
E213615
|
entity |
| Predicate | retirementFromMMA |
P2089
|
FINISHED |
| Object | 2013 |
—
|
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: 2013 | Statement: [Matt Hughes, retirementFromMMA, 2013]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: retirementFromMMA Context triple: [Matt Hughes, retirementFromMMA, 2013]
-
A.
retiredFrom
Indicates that an entity has permanently stopped working for or being active in a specified organization, role, or activity.
-
B.
announcedRetirementFrom
Indicates that an entity has publicly declared its intention to retire from a particular role, position, organization, or activity.
-
C.
retiredTo
Indicates that an entity has permanently left active service or work and taken up residence or status in a particular place or role as their retirement destination.
-
D.
retiredFromRacing
Indicates that an entity has permanently stopped participating in competitive racing activities.
-
E.
retired
chosen
Indicates that an entity has permanently stopped working in their former occupation or role, typically after reaching a certain age or service duration.
- F. None of above.
Provenance (3 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_69ca839add308190b57d53b4ec21f2d0 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdcffa045c8190a08db0bb74cb006a |
completed | April 2, 2026, 2:10 a.m. |
| PD | Predicate disambiguation | batch_69cd4b92573481909389bc6148ae7ea8 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 8:59 p.m.