Triple
T9113385
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holliday Grainger |
E218659
|
entity |
| Predicate | portrayedIn |
P626
|
FINISHED |
| Object | Patrick Melrose |
E42643
|
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: Patrick Melrose | Statement: [Holliday Grainger, portrayedIn, Patrick Melrose]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patrick Melrose Context triple: [Holliday Grainger, portrayedIn, Patrick Melrose]
-
A.
Patrick Melrose
chosen
Patrick Melrose is a British-American television drama miniseries based on Edward St Aubyn’s semi-autobiographical novels, following an aristocratic man's struggle with trauma, addiction, and recovery.
-
B.
Henry Green
Henry Green was a 20th-century English novelist celebrated for his innovative, elliptical prose style and acute portrayals of class and everyday life.
-
C.
The Duke of Flatbush
The Duke of Flatbush was the celebrated Brooklyn Dodgers Hall of Fame center fielder Duke Snider, renowned for his powerful hitting and key role in the team’s 1950s success.
-
D.
Franny
Franny is a common diminutive or nickname for the given name Frances.
-
E.
The Malloys
The Malloys are a directing duo known for their influential and stylish music videos and commercials.
- 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_69ca83dc94ac8190b9ef42684d36ff39 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca84b0a048190964f560f78e27cce |
completed | April 1, 2026, 5:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d07758ce3c819088e78674a7da5a06 |
completed | April 4, 2026, 2:28 a.m. |
Created at: March 30, 2026, 7:16 p.m.