Triple
T19194974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anna Q. Nilsson |
E469942
|
entity |
| Predicate | birthName |
P65
|
FINISHED |
| Object | Anna Quirentia Nilsson |
—
|
NE NERFINISHED |
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: Anna Quirentia Nilsson | Statement: [Anna Q. Nilsson, birthName, Anna Quirentia Nilsson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anna Quirentia Nilsson Context triple: [Anna Q. Nilsson, birthName, Anna Quirentia Nilsson]
-
A.
Anna Q. Nilsson
chosen
Anna Q. Nilsson was a prominent Swedish-born American silent film actress who became one of Hollywood’s earliest female stars in the 1910s and 1920s.
-
B.
Maria Nilsson
Maria Nilsson is an archaeologist known for directing research and excavations at the ancient Egyptian site of Gebel el-Silsila.
-
C.
Emma Nilsson
Emma Nilsson is a person bearing the Swedish surname Nilsson, which is common in Scandinavian countries.
-
D.
Sara Nilsson
Sara Nilsson is a Swedish personal name shared by multiple individuals, most commonly associated with women in Sweden.
-
E.
Nilla Svensdotter
Nilla Svensdotter was the mother of American ventriloquist and actor Edgar Bergen.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f8a4d6b4819083fc5dd4dab05811 |
completed | April 20, 2026, 9:57 a.m. |
Created at: April 10, 2026, 12:07 p.m.