Triple
T87937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tituba |
E1767
|
entity |
| Predicate | confessedTo |
P4081
|
FINISHED |
| Object | practicing witchcraft |
—
|
LITERAL 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: practicing witchcraft | Statement: [Tituba, confessedTo, practicing witchcraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: confessedTo Context triple: [Tituba, confessedTo, practicing witchcraft]
-
A.
usesConfession
Indicates that one entity employs or relies on a confession (typically an admission of guilt or wrongdoing) as part of its actions or reasoning toward another entity or outcome.
-
B.
firstAccused
Indicates that the subject is the primary or earliest individual formally charged or blamed in a particular case or incident.
-
C.
prosecuted
Indicates that legal authorities have formally brought criminal charges against an entity and pursued a case against them in a court of law.
-
D.
confirmedBy
Indicates that one entity validates, approves, or verifies the truth, accuracy, or occurrence of another entity or event.
-
E.
concluded
Indicates that an entity has brought an event, process, discussion, or agreement to an end, often after reaching a decision or final judgment.
- F. None of above. chosen
Provenance (4 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_69a24c8150408190910a693eb51c1f71 |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a2503d304c8190a0034ffa4a38a501 |
completed | Feb. 28, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_69a24eb6da2c8190a33d144d219f7abe |
completed | Feb. 28, 2026, 2:11 a.m. |
| PDg | Predicate description generation | batch_69a2503c12808190a3cbb7b171f466f0 |
completed | Feb. 28, 2026, 2:17 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.