Triple
T3618239
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lilian Swann Saarinen |
E76656
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Swann |
E330624
|
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: Swann | Statement: [Lilian Swann Saarinen, familyName, Swann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Swann Context triple: [Lilian Swann Saarinen, familyName, Swann]
-
A.
Swann
chosen
Swann is a surname most prominently associated with Lynn Swann, a Hall of Fame American football wide receiver and former politician.
-
B.
Maurice
Maurice is a 1987 British romantic drama film, based on E.M. Forster’s novel, that explores same-sex love and class in early 20th-century England.
-
C.
Maurice
Maurice is a masculine given name of Latin origin, commonly used in English and French-speaking countries.
-
D.
Marcel
Marcel is a masculine given name of French origin, commonly used in various European countries.
-
E.
Monsieur
Monsieur was the traditional honorific title used at the French court for Philippe I, Duke of Orléans, the younger brother of King Louis XIV.
- 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_69ad85dae2fc81908d1ceadbc6af0089 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc2b72b3481909f4a09000d1815d9 |
completed | March 8, 2026, 6:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4331a82688190add137b1f68c955e |
completed | March 13, 2026, 3:54 p.m. |
Created at: March 8, 2026, 3:23 p.m.