Triple
T7782067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moses Kotane |
E221543
|
entity |
| Predicate | closeAllyOf |
P2865
|
FINISHED |
| Object | J.B. Marks |
E198568
|
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: J.B. Marks | Statement: [Moses Kotane, closeAllyOf, J.B. Marks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: J.B. Marks Context triple: [Moses Kotane, closeAllyOf, J.B. Marks]
-
A.
J.B. Marks
chosen
J.B. Marks was a South African communist leader and anti-apartheid activist who played a significant role in resistance politics during the mid-20th century.
-
B.
David Marks
David Marks was a British architect best known as the co-designer of the London Eye and other major public structures.
-
C.
David Marks
David Marks is an American guitarist and singer best known as an early member of the iconic rock band The Beach Boys.
-
D.
Bill Marks
Bill Marks is the troubled yet determined U.S. federal air marshal portrayed by Liam Neeson in the action-thriller film "Non-Stop."
-
E.
Dave Marks
Dave Marks is a character on "The Jim Gaffigan Show," serving as one of Jim's close friends and a source of comic relief in his everyday misadventures.
- 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_69ca83ebbef881909ac47f789145fef7 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cadf1dcc6c8190b3c6ee4ff7808e02 |
completed | March 30, 2026, 8:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69caf5d30c748190bbb71534cfdf4f75 |
completed | March 30, 2026, 10:14 p.m. |
Created at: March 30, 2026, 4:21 p.m.