Triple
T87948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tituba |
E1767
|
entity |
| Predicate | sourceOfInformation |
P2296
|
FINISHED |
| Object | court records of Salem witch trials |
—
|
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: court records of Salem witch trials | Statement: [Tituba, sourceOfInformation, court records of Salem witch trials]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceOfInformation Context triple: [Tituba, sourceOfInformation, court records of Salem witch trials]
-
A.
source
Indicates that something originates from, is derived from, or is provided by a particular entity or location.
-
B.
primarySources
chosen
Indicates that one entity serves as an original, authoritative source of information or evidence for another entity.
-
C.
languageOfSources
Indicates that the specified language is the language in which the referenced sources or source materials are expressed.
-
D.
sourceRegion
Indicates the geographic or spatial region from which something originates or is derived.
-
E.
citation
Indicates that one entity references, quotes, or otherwise acknowledges another entity as a source of information or authority.
- F. None of above.
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_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. |
Created at: Feb. 28, 2026, 2:06 a.m.