Triple
T9990096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yam |
E196863
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Prince Sea |
E834358
|
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: Prince Sea | Statement: [Yam, title, Prince Sea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prince Sea Context triple: [Yam, title, Prince Sea]
-
A.
Prince Sea
chosen
Prince Sea is an alias of the artist and producer Yam, known for their work in contemporary music.
-
B.
King Triton
King Triton is the powerful and protective sea king and father of Ariel in Disney’s animated film "The Little Mermaid."
-
C.
Prinze
Prinze is the surname of American actor Freddie Prinze Jr., associated with a family of entertainers in film and television.
-
D.
Prince Sirki
Prince Sirki is the personified figure of Death who assumes human form to experience life and love in the play and film "Death Takes a Holiday."
-
E.
Prince Noah of Nassau
Prince Noah of Nassau is a younger member of Luxembourg’s grand ducal family, known as the son of Prince Louis of Luxembourg and a grandson of Grand Duke Henri.
- 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_69ca82f1678c819093d06320a05f16a4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdc7a0cb6481908d7bd1b43f93bd18 |
completed | April 2, 2026, 1:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d26a21b2388190b16f0aa142846599 |
completed | April 5, 2026, 1:56 p.m. |
Created at: March 30, 2026, 8:50 p.m.