Triple
T17009000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Marks |
E412648
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Michael Marks |
E412648
|
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: Michael Marks | Statement: [Michael Marks, name, Michael Marks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Marks Context triple: [Michael Marks, name, Michael Marks]
-
A.
Michael Marks
chosen
Michael Marks was a Polish-born British businessman best known as the co-founder of the major retail chain Marks & Spencer.
-
B.
Larry Marks
Larry Marks is a music producer best known for his work on Phil Ochs’ influential 1967 album "Pleasures of the Harbor."
-
C.
Alvin Marks
Alvin Marks was an American inventor known for his work on advanced energy technologies and high-efficiency lighting concepts.
-
D.
Herbert H. Marks
Herbert H. Marks was a notable individual distinguished enough in his field or public life to be recognized as a prominent bearer of the surname Marks.
-
E.
Maurice Richlin
Maurice Richlin was an American screenwriter best known for co-writing classic films such as "The Pink Panther" and "Operation Petticoat."
- 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d3853f548190910240a2145cc890 |
completed | April 18, 2026, 6:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b46e89c81908271eb22b535c558 |
completed | May 10, 2026, 11:56 p.m. |
Created at: April 10, 2026, 5:33 a.m.