Triple

T3589371
Position Surface form Disambiguated ID Type / Status
Subject William Good E75988 entity
Predicate spouse P13 FINISHED
Object Sarah Good E11591 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: Sarah Good | Statement: [William Good, spouse, Sarah Good]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Good
Context triple: [William Good, spouse, Sarah Good]
  • A. Sarah Good chosen
    Sarah Good was one of the first women accused and executed for witchcraft during the 1692 Salem witch trials in colonial Massachusetts.
  • B. Rebecca Nurse
    Rebecca Nurse was a respected elderly Puritan woman in colonial Massachusetts who became one of the most famous individuals executed during the Salem witch trials.
  • C. Susannah Parris
    Susannah Parris was a member of the Parris family in late 17th-century Salem, historically noted as a sibling of accuser Elizabeth Parris during the Salem witch trials era.
  • D. Martha Corey
    Martha Corey was a devout, outspoken resident of Salem Village whose 1692 execution for witchcraft became one of the most infamous injustices of the Salem witch trials.
  • E. Abigail Williams
    Abigail Williams is a central, manipulative accuser in Arthur Miller’s play *The Crucible*, whose lies help fuel the Salem witch trials.
  • 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_69ad85d6dc3c8190b491b79b83e25461 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc13c9514819096adf60b15016b8b completed March 8, 2026, 6:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69b43305b21081909d7f78dac96ceaa8 completed March 13, 2026, 3:53 p.m.
Created at: March 8, 2026, 3:22 p.m.