Triple
T23307215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Gracie |
E590482
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Gomes |
—
|
NE NERFINISHED |
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: Gomes | Statement: [Roger Gracie, familyName, Gomes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gomes Context triple: [Roger Gracie, familyName, Gomes]
-
A.
Gomes
chosen
Gomes is a common Portuguese surname shared by many individuals, including the artist Fernanda Gomes.
-
B.
Jean Gomes
Jean Gomes is a leadership and performance expert known for co-authoring influential business books on productivity, well-being, and organizational change.
-
C.
Fernando Gomes
Fernando Gomes is a Portuguese sports executive best known for serving as president of the Portuguese Football Federation and holding influential roles in European and international football governance.
-
D.
Andrade
Andrade is a common Portuguese and Spanish surname borne by numerous notable figures across fields such as sports, politics, and the arts.
-
E.
Guilherme
Guilherme is the Portuguese form of the given name William, commonly used in Portuguese-speaking countries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d1c0ecc8190a355aa229f06d0e0 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1972846fc819092ca2b9590b2e177 |
completed | April 29, 2026, 5:29 a.m. |
Created at: April 17, 2026, 5:05 p.m.