Triple
T10180885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laetitia |
E236777
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Lettice |
E289047
|
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: Lettice | Statement: [Laetitia, hasVariant, Lettice]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lettice Context triple: [Laetitia, hasVariant, Lettice]
-
A.
Letitia
chosen
Letitia is a feminine given name of Latin origin, commonly associated with the meaning "joy" or "happiness."
-
B.
Marjory
Marjory is a feminine given name, commonly considered a variant spelling of Marjorie.
-
C.
Henrietta Somerset
Henrietta Somerset was an English noblewoman of the late 17th and early 18th centuries, a member of the prominent Somerset family who married into the ducal house of Grafton.
-
D.
Lady Rowley
Lady Rowley is a British aristocratic matriarch character, best known as the socially ambitious mother in Anthony Trollope’s novel "He Knew He Was Right."
-
E.
Rosamund
Rosamund was a 6th-century Lombard queen best known for orchestrating the assassination of her husband, King Alboin, in revenge for his brutal treatment of her family.
- 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_69ca84d7260c8190bfbec36762943f37 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cded315f14819085727bd9b4363d10 |
completed | April 2, 2026, 4:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d31792490c819088c89444f75cdbc9 |
completed | April 6, 2026, 2:16 a.m. |
Created at: March 30, 2026, 9:11 p.m.