Triple
T18927755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanisivik |
E463017
|
entity |
| Predicate | settlementEstablished |
P156
|
FINISHED |
| Object | mid-1970s |
—
|
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: mid-1970s | Statement: [Nanisivik, settlementEstablished, mid-1970s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: settlementEstablished Context triple: [Nanisivik, settlementEstablished, mid-1970s]
-
A.
settledAs
Indicates that one entity has been resolved, finalized, or agreed upon in the form or status of another entity.
-
B.
settlementWith
Indicates a relationship where one party reaches or maintains a settlement or agreement with another party, typically resolving a dispute or claim.
-
C.
settlementState
Indicates the state or status of a settlement process or transaction at a given point in time.
-
D.
settled
chosen
Indicates that an entity established residence or a stable presence in a place, typically after moving from elsewhere.
-
E.
establishedTo
Indicates that one entity was created, founded, or set up for the purpose of serving, supporting, or enabling 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c9bdddb481908bebd32f927ed5de |
completed | April 20, 2026, 6:37 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 11:59 a.m.