Triple
T2321184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halden Historical Society |
E51182
|
entity |
| Predicate | sharesKnowledgeThrough |
P4471
|
FINISHED |
| Object | public programs |
—
|
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: public programs | Statement: [Halden Historical Society, sharesKnowledgeThrough, public programs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesKnowledgeThrough Context triple: [Halden Historical Society, sharesKnowledgeThrough, public programs]
-
A.
knowledgeExchange
chosen
Indicates a reciprocal sharing or transfer of knowledge, information, or expertise between entities.
-
B.
sharesUniverseWith
Indicates that two entities exist within the same fictional or narrative universe, implying shared continuity, setting, or canon.
-
C.
sharesPlatformWith
Indicates that two entities operate on, are available through, or participate within the same platform or system.
-
D.
sharesResourcesWith
Indicates that two entities mutually use, access, or allocate the same resources.
-
E.
sharesIn
Indicates that one entity holds or possesses shares or ownership stakes in another entity.
- 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_69a88b074b908190ae983dbca7757d88 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc685f05481909c863b29d1f6bacd |
completed | March 7, 2026, 6:32 a.m. |
| PD | Predicate disambiguation | batch_69abc5909cc48190aab257313542dc49 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:49 p.m.