Triple
T2847381
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fortnum & Mason |
E63012
|
entity |
| Predicate | knownAs |
P39
|
FINISHED |
| Object | Fortnum’s |
E63012
|
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: Fortnum’s | Statement: [Fortnum & Mason, knownAs, Fortnum’s]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fortnum’s Context triple: [Fortnum & Mason, knownAs, Fortnum’s]
-
A.
Fortnum & Mason
chosen
Fortnum & Mason is a historic and prestigious British department store in London, renowned for its luxury food halls, hampers, and fine goods.
-
B.
Hatchards
Hatchards is a historic London bookshop, founded in 1797 and renowned as one of the oldest and most prestigious bookstores in the United Kingdom.
-
C.
Harrods
Harrods is a world-famous luxury department store in London renowned for its upscale shopping, elaborate food halls, and iconic Knightsbridge location.
-
D.
Cluett Peabody & Company
Cluett Peabody & Company was a prominent American clothing manufacturer best known for its Arrow brand shirts and collars and its influential early 20th-century advertising campaigns.
-
E.
Hamleys
Hamleys is a world-famous British toy store chain best known for its flagship multi-storey shop in central London.
- 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_69ab4c407c408190857d25e027155ce9 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf3ebbac819090e2bf98ed9fbd02 |
completed | March 7, 2026, 8:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b055d9c0f08190b62afbc1bf98dc20 |
completed | March 10, 2026, 5:33 p.m. |
Created at: March 6, 2026, 10:02 p.m.