Triple
T8946982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Olsen |
E213244
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Olsen |
E656487
|
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: Olsen | Statement: [Elizabeth Olsen, familyName, Olsen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olsen Context triple: [Elizabeth Olsen, familyName, Olsen]
-
A.
Olsen
chosen
Olsen is a common Scandinavian-origin surname borne by numerous notable individuals across sports, entertainment, and other fields.
-
B.
Olson
Olson is a surname most prominently associated in entertainment with American actress and comedian Kaitlin Olson.
-
C.
Sarah Olson
Sarah Olson is a film producer best known for her work on the feminist documentary "Miss Representation," which examines the portrayal of women in the media.
-
D.
Nilsen
Nilsen is a surname, primarily of Scandinavian origin, that serves as a variant spelling of Nelson.
-
E.
Ole
Ole is a masculine given name of Scandinavian origin, commonly used in Norway and Denmark.
- 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_69ca839843408190a39069a029a89f15 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66deb8ec819087a9c5eddd24c08a |
completed | April 1, 2026, 12:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc2022e30819089ba08f494a3a66f |
completed | April 3, 2026, 1:34 p.m. |
Created at: March 30, 2026, 6:59 p.m.