Triple
T10253629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julian Savea |
E240406
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | Julian Savea |
E240406
|
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: Julian Savea | Statement: [Julian Savea, fullName, Julian Savea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Julian Savea Context triple: [Julian Savea, fullName, Julian Savea]
-
A.
Julian Savea
chosen
Julian Savea is a powerful New Zealand rugby union wing renowned for his prolific try-scoring for the All Blacks and his dominant performances on the international stage.
-
B.
Andrew Sarlo
Andrew Sarlo is a music producer known for his work with indie and alternative artists such as Big Thief and Bon Iver.
-
C.
Jonathan Benassaya
Jonathan Benassaya is a French entrepreneur best known for co-founding the music streaming service Deezer.
-
D.
Julian Kirrin
Julian Kirrin is the sensible, responsible eldest cousin and de facto leader of the children’s adventures in Enid Blyton’s Famous Five series.
-
E.
Julian Breece
Julian Breece is an American screenwriter and producer known for his work on socially conscious film and television projects, including co-writing the biographical drama "Rustin" (2023).
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d381a7e198819090280d5ab885d59e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d23f106c81909c1ce20a2ffa86ea |
completed | April 7, 2026, 9:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71cd263748190b02540b007c5453d |
completed | April 9, 2026, 3:28 a.m. |
Created at: April 6, 2026, 11:29 a.m.