Triple
T3393397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Harper |
E71469
|
entity |
| Predicate | creatorPseudonym |
P3799
|
FINISHED |
| Object | Mark Twain |
E586
|
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: Mark Twain | Statement: [Joe Harper, creatorPseudonym, Mark Twain]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Twain Context triple: [Joe Harper, creatorPseudonym, Mark Twain]
-
A.
Mark Twain
chosen
Mark Twain was a renowned 19th-century American author and humorist, best known for works like "The Adventures of Tom Sawyer" and "Adventures of Huckleberry Finn."
-
B.
Pleasant Hannibal Clemens
Pleasant Hannibal Clemens was a relative of the American author Mark Twain (Samuel Langhorne Clemens), belonging to the Clemens family.
-
C.
Langdon Clemens
Langdon Clemens was the firstborn son of American author Mark Twain (Samuel Clemens), who died in infancy.
-
D.
John Howells
John Howells is a notable individual who shares the surname associated with the prominent Howells family name.
-
E.
John Mead Howells
John Mead Howells was an American architect best known for his influential skyscraper designs in the early 20th century and his role in shaping Chicago’s and New York’s urban skylines.
- 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_69ad85a9c4a88190a854019341cb3b60 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb853746c8190bfa1447e6ebbefb3 |
completed | March 8, 2026, 5:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b35464d9a88190aec3a7597cecff21 |
completed | March 13, 2026, 12:03 a.m. |
Created at: March 8, 2026, 3:14 p.m.