Triple
T6245500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Blueprint for Murder |
E139710
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Jean Peters |
E268230
|
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: Jean Peters | Statement: [A Blueprint for Murder, starring, Jean Peters]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean Peters Context triple: [A Blueprint for Murder, starring, Jean Peters]
-
A.
Jean Peters
chosen
Jean Peters was an American film actress best known for her leading roles in 1940s and 1950s Hollywood adventure and drama films.
-
B.
Charles F. Roos
Charles F. Roos was an American economist and mathematician known for his pioneering work in econometrics and contributions to the formalization of economic theory.
-
C.
James Nourse
James Nourse was an 18th-century British sea captain involved in the transatlantic slave trade.
-
D.
Carl Schenkel
Carl Schenkel was a Swiss film director known for his work on thrillers and adventure films in both European and Hollywood cinema.
-
E.
John Clarence Karcher
John Clarence Karcher was an American geophysicist and pioneer of reflection seismology whose work helped lay the foundations of modern petroleum exploration.
- 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_69c008b1c5088190ae6de2555fc05ad8 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0631d9e648190a59ab4001f506424 |
completed | March 22, 2026, 9:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6d4fdd7288190bb9aef680beb906d |
completed | March 27, 2026, 7:05 p.m. |
Created at: March 22, 2026, 4:23 p.m.