Triple
T20338703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Crusades (1935 film) |
E495683
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Harold Lamb |
—
|
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: Harold Lamb | Statement: [The Crusades (1935 film), screenwriter, Harold Lamb]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harold Lamb Context triple: [The Crusades (1935 film), screenwriter, Harold Lamb]
-
A.
Harold Lamb
chosen
Harold Lamb was an American historian, novelist, and screenwriter best known for his popular biographies and adventure stories set in Asian and Middle Eastern historical contexts.
-
B.
Harold March
Harold March is a fictional character featured in G.K. Chesterton’s Father Brown stories, notably in the novel "The Man Who Knew Too Much."
-
C.
H. M. Harwood
H. M. Harwood was a British playwright and screenwriter active in the early 20th century, known for his work on stage adaptations and films.
-
D.
Walter Connolly
Walter Connolly was an American character actor of the 1930s known for his comic and often blustery supporting roles in Hollywood films.
-
E.
James Norman Hall
James Norman Hall was an American author and World War I veteran best known for co-writing the classic historical novel "Mutiny on the Bounty" and its sequels.
- 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_69e0b4a1a09881908d97270d6971a25a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678332bd08190a83880fb6aa32e08 |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:23 a.m.