Triple
T6490132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucy Morris |
E148013
|
entity |
| Predicate | publisherOfWork |
P1760
|
FINISHED |
| Object | Virtue & Co. |
E107008
|
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: Virtue & Co. | Statement: [Lucy Morris, publisherOfWork, Virtue & Co.]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Virtue & Co. Context triple: [Lucy Morris, publisherOfWork, Virtue & Co.]
-
A.
Virtue & Co.
chosen
Virtue & Co. was a 19th-century British publishing firm known for producing literary works, including those of Anthony Trollope such as "Phineas Finn."
-
B.
Liberty & Co.
Liberty & Co. is a historic London-based department store and design firm renowned for its influential role in popularizing Art Nouveau style in Britain and abroad.
-
C.
Vanity Fair Brands
Vanity Fair Brands is an apparel company known for producing intimate wear and lingerie under various well-recognized brands.
-
D.
Marchesa
Marchesa is a luxury fashion label renowned for its ornate, red-carpet-ready eveningwear and bridal gowns.
-
E.
Marchesa
Marchesa is the Italian noble title traditionally used to designate a woman holding the rank of marquess.
- 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_69c009088f3081909cd467b05919de30 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c06a9926fc81909db0f390e385e97d |
completed | March 22, 2026, 10:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c653ba03288190ba4e4ce99d0ba32e |
completed | March 27, 2026, 9:54 a.m. |
Created at: March 22, 2026, 4:52 p.m.