Triple
T35885849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thiago Alves |
E1037639
|
entity |
| Predicate | yearsActiveAsFighter |
P122417
|
FINISHED |
| Object | 2001–2020s |
—
|
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: 2001–2020s | Statement: [Thiago Alves, yearsActiveAsFighter, 2001–2020s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearsActiveAsFighter Context triple: [Thiago Alves, yearsActiveAsFighter, 2001–2020s]
-
A.
yearsActiveAsBoxer
Indicates the span of time, measured in years, during which an individual was actively engaged in boxing.
-
B.
yearsActiveInMMA
chosen
Indicates the span of time, in years, during which an entity has been actively involved in mixed martial arts competition or participation.
-
C.
activeYearsInBoxingPromotion
Indicates the span of years during which an entity was actively involved with a particular boxing promotion.
-
D.
lastProfessionalFightDate
Indicates the calendar date on which an entity most recently participated in a professional fight.
-
E.
finalProfessionalFightYear
Indicates the year in which an individual participated in their last professional fight.
- 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_69f76e1f4d748190bb55594d8441d70e |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa3883d48190b05e3d2da7a017ae |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d435288190b30b1991fb003121 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.