Triple
T19129967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruth Putnam |
E468289
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | Thomas Putnam |
—
|
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: Thomas Putnam | Statement: [Ruth Putnam, father, Thomas Putnam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Putnam Context triple: [Ruth Putnam, father, Thomas Putnam]
-
A.
Thomas Putnam
chosen
Thomas Putnam was a prominent and influential accuser during the Salem witch trials, known for aggressively pursuing witchcraft charges against many of his neighbors.
-
B.
Samuel Putnam
Samuel Putnam was an American writer, translator, and literary critic best known for his influential English translation of Miguel de Cervantes' "Don Quixote."
-
C.
Nathaniel Hathorne Sr.
Nathaniel Hathorne Sr. was a New England sea captain and the father of American novelist Nathaniel Hawthorne.
-
D.
Tom Putnam
Tom Putnam is a film producer and director best known for his work on the acclaimed documentary "Marwencol."
-
E.
Ann Putnam Sr.
Ann Putnam Sr. was a prominent and influential accuser during the Salem witch trials of 1692 in colonial Massachusetts.
- 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_69d8dd0796a48190b34ce4cd9d3f3be5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e3e8c49481908b6be87af54d12cf |
completed | April 20, 2026, 8:29 a.m. |
Created at: April 10, 2026, 12:05 p.m.