Triple
T17549170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lamfrom |
E427409
|
entity |
| Predicate | usedAsSurnameBy |
P18
|
FINISHED |
| Object | Paul Lamfrom |
—
|
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: Paul Lamfrom | Statement: [Lamfrom, usedAsSurnameBy, Paul Lamfrom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Lamfrom Context triple: [Lamfrom, usedAsSurnameBy, Paul Lamfrom]
-
A.
Paul Lamfrom
chosen
Paul Lamfrom was a German-born businessman and patriarch of the family that built Columbia Sportswear into a major global outdoor apparel company.
-
B.
Gordon Lamont
Gordon Lamont is an actor known for his role in the film "The Purifiers."
-
C.
Anthony Lamb
Anthony Lamb is an American professional basketball player known for his versatility as a forward and his stints in the NBA and G League.
-
D.
Andrew Lamb
Andrew Lamb is a name shared by several notable individuals, including professionals in fields such as engineering, music, and politics.
-
E.
Peter Lambert
Peter Lambert is a film editor best known for his work on the satirical political comedy "The Death of Stalin."
- 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e45463ddf88190a2c29f3246adcb6e |
completed | April 19, 2026, 4:04 a.m. |
Created at: April 10, 2026, 5:49 a.m.