Triple
T3551824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kanin Peninsula |
E75126
|
entity |
| Predicate | humanSettlementPattern |
P1830
|
FINISHED |
| Object | scattered small settlements |
—
|
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: scattered small settlements | Statement: [Kanin Peninsula, humanSettlementPattern, scattered small settlements]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: humanSettlementPattern Context triple: [Kanin Peninsula, humanSettlementPattern, scattered small settlements]
-
A.
hadPrimarySettlementPattern
chosen
Indicates that an entity exhibited or was characterized by a particular dominant form or arrangement of human settlement.
-
B.
humanSettlementType
Indicates the classification of a human settlement based on its form or function, such as village, town, or city.
-
C.
humanSettlementStatus
Indicates the classification of a place in terms of its status as a human settlement (e.g., whether and how it is recognized or designated as a populated place).
-
D.
traditionalSettlement
Indicates that an entity is a settlement characterized by long-established, customary, or historically rooted patterns of habitation and land use.
-
E.
humanSettlementInside
Indicates that one human settlement is located entirely within the geographic boundaries of another area or settlement.
- 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_69ad85d33c6c819081d5ac1df13b5680 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc05256f081908b8d6a5df917e679 |
completed | March 8, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69adb83270ac819083967db0570167d2 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:20 p.m.