Triple
T8872198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angela |
E211185
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Angelina |
E300797
|
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: Angelina | Statement: [Angela, hasVariant, Angelina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angelina Context triple: [Angela, hasVariant, Angelina]
-
A.
Angelina
chosen
Angelina is the given name of Princess Angeline, the eldest daughter of Chief Seattle and a notable figure in Seattle’s early history.
-
B.
Jolie
Jolie is a nickname for Al Jolson, the influential early 20th-century American singer and entertainer often called "the world's greatest entertainer."
-
C.
Jolie Gabor
Jolie Gabor was a Hungarian-American jeweler and socialite best known as the glamorous matriarch of the Gabor family of actresses and celebrities.
-
D.
Lisa Origliasso
Lisa Origliasso is an Australian singer-songwriter best known as one half of the pop duo The Veronicas.
-
E.
Melanie Truhett
Melanie Truhett is an American television producer and talent manager known for her work in comedy and for her long-time collaboration and marriage with comedian Brian Posehn.
- 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_69ca838e78748190934d82db3104f855 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61281e888190a32b08980310979f |
completed | April 1, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa0f1f1888190a5b514b895e44799 |
completed | April 3, 2026, 11:13 a.m. |
Created at: March 30, 2026, 6:51 p.m.