Triple
T18121380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Luckman |
E433740
|
entity |
| Predicate | hasSurname |
P18
|
FINISHED |
| Object | Luckman |
—
|
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: Luckman | Statement: [Charles Luckman, hasSurname, Luckman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luckman Context triple: [Charles Luckman, hasSurname, Luckman]
-
A.
Luckman
chosen
Luckman is a surname most notably associated with Charles Luckman, an American architect and businessman known for designing prominent mid-20th-century buildings.
-
B.
Johnny Sain
Johnny Sain was an American Major League Baseball pitcher and renowned pitching coach, best known as a star hurler for the Boston Braves in the 1940s.
-
C.
Mickey Hutton
Mickey Hutton is a British comedian and actor known for his work in television and film, including roles in crime drama series.
-
D.
Bumper Robinson
Bumper Robinson is an American actor and voice actor known for his extensive work in animation, video games, and television since childhood.
-
E.
Elvin Smith
Elvin Smith is a songwriter best known for co-writing the hit ballad "Lay Me Down."
- 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_69d8b909e8cc81908df4cc2b8ea6d11f |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddea61bc8190af4b3efa2596b632 |
completed | April 19, 2026, 1:51 p.m. |
Created at: April 10, 2026, 10:28 a.m.