Triple
T5454100
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heart of Darkness |
E122437
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Joseph Conrad |
E83816
|
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: Joseph Conrad | Statement: [Heart of Darkness, author, Joseph Conrad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joseph Conrad Context triple: [Heart of Darkness, author, Joseph Conrad]
-
A.
Joseph Conrad
chosen
Joseph Conrad was a Polish-British novelist renowned for his psychologically complex, morally ambiguous sea tales and modernist works such as "Heart of Darkness" and "Lord Jim."
-
B.
A. R. Simoun
A. R. Simoun is a screenwriter best known for his work on the horror film "The Serpent and the Rainbow."
-
C.
Paul Hymans
Paul Hymans was a Belgian statesman and diplomat who played a key role in the founding of the League of Nations and served as one of its early presidents.
-
D.
Jack London
Jack London was an American novelist and short-story writer best known for adventure classics such as "The Call of the Wild" and "White Fang."
-
E.
Jack London
Jack London is a fictional protagonist from the comic book series "The Secret Service," around whom the story’s espionage-driven plot revolves.
- 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_69bd46424248819085282ddf50a565f3 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd91ed9a388190967e7ffaf9dbadc6 |
completed | March 20, 2026, 6:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf4140248081908c7f42b91579a837 |
completed | March 22, 2026, 1:09 a.m. |
Created at: March 20, 2026, 2:08 p.m.