Triple
T15078077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Suzan Farmer |
E380058
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Christopher Lee |
E18510
|
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: Christopher Lee | Statement: [Suzan Farmer, associatedWith, Christopher Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Christopher Lee Context triple: [Suzan Farmer, associatedWith, Christopher Lee]
-
A.
Christopher Lee
chosen
Christopher Lee was an English actor renowned for his deep voice and imposing presence, best known for iconic roles such as Count Dracula in Hammer Horror films and Saruman in "The Lord of the Rings" trilogy.
-
B.
Peter Cushing
Peter Cushing was an English actor best known for his roles in classic Hammer horror films and as Grand Moff Tarkin in Star Wars.
-
C.
Ian Menzies
Ian Menzies is a notable individual who shares the Menzies surname, recognized as a distinguished bearer of that family name.
-
D.
Michael Ironside
Michael Ironside is a Canadian actor known for his intense, often villainous roles in science fiction and action films such as "Total Recall," "Starship Troopers," and "Top Gun."
-
E.
Guy Moore
Guy Moore is a film editor known for his work on the James Bond movie "Tomorrow Never Dies."
- 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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dff7fe5a208190823900b25e298dab |
completed | April 15, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5d4f6a48190aeb42341b0c395a7 |
completed | May 9, 2026, 3:11 a.m. |
Created at: April 10, 2026, 3:03 a.m.