Triple
T17327928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosamond Vivian |
E420734
|
entity |
| Predicate | fleesFrom |
P11257
|
FINISHED |
| Object | Philip Tempest |
—
|
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: Philip Tempest | Statement: [Rosamond Vivian, fleesFrom, Philip Tempest]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Philip Tempest Context triple: [Rosamond Vivian, fleesFrom, Philip Tempest]
-
A.
Philip Tempest
chosen
Philip Tempest is the dark, obsessive villain of Louisa May Alcott’s gothic novel "A Long Fatal Love Chase," relentlessly pursuing the heroine across Europe.
-
B.
John Cheke
John Cheke was a 16th-century English classical scholar and royal tutor who became a prominent Protestant intellectual and statesman during the reign of Edward VI.
-
C.
Nigel Tangye
Nigel Tangye was a British writer, aviation enthusiast, and former Royal Navy officer known for his books on flying and his marriage to actress Ann Todd.
-
D.
Michael S. Paterson
Michael S. Paterson is a British computer scientist and mathematician known for his contributions to theoretical computer science and combinatorial game theory.
-
E.
Nigel Shadbolt
Nigel Shadbolt is a British computer scientist and artificial intelligence researcher known for his leading role in promoting open data and digital governance.
- 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_69d889d3adc881909319f1edb8d2a956 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439d42154819093a240f677a63145 |
completed | April 19, 2026, 2:11 a.m. |
Created at: April 10, 2026, 5:43 a.m.