Triple
T18198071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mari Blanchard |
E435711
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | The Crooked Web |
—
|
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: The Crooked Web | Statement: [Mari Blanchard, notableWork, The Crooked Web]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Crooked Web Context triple: [Mari Blanchard, notableWork, The Crooked Web]
-
A.
The Crooked Web
chosen
The Crooked Web is a 1955 American film noir crime drama featuring Frank Lovejoy in a tense story of deception and double-crosses.
-
B.
A Tangled Web
A Tangled Web is a humorous and romantic novel by Lucy Maud Montgomery that follows the intertwined lives and secrets of an extended Canadian family competing to inherit a prized heirloom.
-
C.
Caught in the Web
Caught in the Web is a 2012 Chinese drama film directed by Chen Kaige that explores the impact of internet shaming and media sensationalism on a young woman’s life.
-
D.
The Crooked Way
The Crooked Way is a 1949 American film noir crime drama about an amnesiac war veteran drawn into a violent criminal underworld.
-
E.
The Woman in the Web
The Woman in the Web is a silent-era American film serial, produced in the 1910s, known for its suspenseful, chapter-based storytelling.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e0d47f1c819082eec59492497797 |
completed | April 19, 2026, 2:04 p.m. |
Created at: April 10, 2026, 10:31 a.m.