Triple
T2069083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nicholas Wisdom |
E45973
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Fredricka Inger |
E45973
|
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: Fredricka Inger | Statement: [Nicholas Wisdom, mother, Fredricka Inger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fredricka Inger Context triple: [Nicholas Wisdom, mother, Fredricka Inger]
-
A.
Fredricka Inger
chosen
Fredricka Inger is best known as the wife of British comedian and actor Norman Wisdom.
-
B.
Werna Gerhardsen
Werna Gerhardsen was a Norwegian politician and Labour Party activist, best known as the influential wife and political partner of long-serving prime minister Einar Gerhardsen.
-
C.
Inger Skramstad
Inger Skramstad is known as the spouse of Norwegian-American physicist and Nobel laureate Ivar Giaever.
-
D.
Charlotte Landelius
Charlotte Landelius is a film editor known for her work on the documentary "I Am Greta," which follows climate activist Greta Thunberg.
-
E.
Josephine Skriver
Josephine Skriver is a Danish fashion model best known for her high-profile runway and print work, including serving as a Victoria’s Secret Angel.
- 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_69a8891b38288190abd572ccad9b6928 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb9f51a008190aead0173a9289204 |
completed | March 7, 2026, 5:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae305263f88190b448fb134163d5aa |
completed | March 9, 2026, 2:28 a.m. |
Created at: March 4, 2026, 7:41 p.m.