Triple
T20947084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martin A. Marks |
E515870
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object | Martin A. Marks |
—
|
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: Martin A. Marks | Statement: [Martin A. Marks, hasName, Martin A. Marks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martin A. Marks Context triple: [Martin A. Marks, hasName, Martin A. Marks]
-
A.
Martin A. Marks
chosen
Martin A. Marks is an individual notable enough to be specifically cited as a distinguished bearer of the surname Marks.
-
B.
Laurence Marks
Laurence Marks is a British television writer and producer best known for co-creating popular sitcoms such as "Birds of a Feather" and "Goodnight Sweetheart."
-
C.
Edward A. Garmatz
Edward A. Garmatz was a long-serving U.S. Congressman from Maryland who represented Baltimore in the House of Representatives in the mid-20th century.
-
D.
Phillip M. Margolin
Phillip M. Margolin is an American author best known for his fast-paced legal thrillers drawing on his experience as a criminal defense attorney.
-
E.
Jack N. Berkman
Jack N. Berkman was a benefactor whose support and legacy are honored through the naming of the Berkman Klein Center for Internet & Society at Harvard University.
- 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_69e0b4fcd678819087a304291f14330a |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fad97aa48190b4be692e3afce8c9 |
completed | April 21, 2026, 4:19 a.m. |
Created at: April 16, 2026, 12:57 p.m.