Triple
T17311519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucy Gaskell |
E420308
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Waterloo Road |
—
|
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: Waterloo Road | Statement: [Lucy Gaskell, notableWork, Waterloo Road]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waterloo Road Context triple: [Lucy Gaskell, notableWork, Waterloo Road]
-
A.
Waterloo Road
Waterloo Road is a major thoroughfare in central London running near Waterloo station and connecting key cultural and commercial areas on the South Bank.
-
B.
Waterloo Road
chosen
Waterloo Road is a British television drama series set in a troubled comprehensive school, focusing on the lives of its teachers and students.
-
C.
Trafalgar Road
Trafalgar Road is a major thoroughfare in New Kingston, Jamaica, known for its commercial activity and central location within the city’s business district.
-
D.
Outram Road
Outram Road is a major thoroughfare in Singapore’s Outram district, linking key residential, commercial, and medical areas near the city center.
-
E.
Regent Road
Regent Road is a street in Altrincham, Greater Manchester, forming part of the town centre’s local road network and commercial area.
- 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439993bac8190a72f6af529bd7cce |
completed | April 19, 2026, 2:10 a.m. |
Created at: April 10, 2026, 5:43 a.m.