Triple
T7106857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Casket Letters controversy |
E165610
|
entity |
| Predicate | documentsNow |
P74937
|
FINISHED |
| Object | lost or destroyed originals |
—
|
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: lost or destroyed originals | Statement: [Casket Letters controversy, documentsNow, lost or destroyed originals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: documentsNow Context triple: [Casket Letters controversy, documentsNow, lost or destroyed originals]
-
A.
documentsCommunity
Indicates that an entity records, describes, or provides information about a particular community.
-
B.
documentsPeriod
Indicates that one entity documents, records, or provides written evidence about a specific time period associated with another entity.
-
C.
documentNumber
Indicates the unique identifying number assigned to a specific document in the relationship.
-
D.
documentAtIssue
Indicates that a particular document is the specific item under consideration or dispute in a given context or proceeding.
-
E.
documentForm
Indicates the specific format or structural type in which a document is presented or recorded.
- 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_69c6888120f081908f8f01b201dc4a4c |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e5b9f13c8190a14898f241ec17a4 |
completed | March 27, 2026, 8:16 p.m. |
| PD | Predicate disambiguation | batch_69c6e1c313e481908b61a23fc89f9332 |
completed | March 27, 2026, 8 p.m. |
| PDg | Predicate description generation | batch_69c6e4a15b088190bee9a23e94aaac53 |
completed | March 27, 2026, 8:12 p.m. |
Created at: March 27, 2026, 2:42 p.m.