Triple
T8532314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nizhyn |
E201982
|
entity |
| Predicate | historicallyHadCommunity |
P11485
|
FINISHED |
| Object | Greek merchants |
—
|
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: Greek merchants | Statement: [Nizhyn, historicallyHadCommunity, Greek merchants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicallyHadCommunity Context triple: [Nizhyn, historicallyHadCommunity, Greek merchants]
-
A.
hasHistoricCommunity
chosen
Indicates that an entity is associated with, contains, or is part of a community of historical significance.
-
B.
hasCommunityIn
Indicates that a community is present, active, or established within a specified location, platform, or context.
-
C.
hasTraditionalCommunity
Indicates that an entity possesses or is associated with a community that maintains traditional practices, customs, or ways of life.
-
D.
hasCommunityArea
Indicates that an entity is associated with, located in, or belongs to a particular community area.
-
E.
foundedCommunity
Indicates that an entity established or created a community, organization, or group.
- 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_69ca832355b08190b8b6a4ab4a4a3554 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe676e2ac8190b65a3d2a935776fd |
completed | March 31, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69cbd111bf988190be98c92a607c6456 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:17 p.m.