Triple
T27412126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harmil Island |
E692180
|
entity |
| Predicate | inhabitationStatus |
P45137
|
FINISHED |
| Object | sparsely inhabited |
—
|
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: sparsely inhabited | Statement: [Harmil Island, inhabitationStatus, sparsely inhabited]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inhabitationStatus Context triple: [Harmil Island, inhabitationStatus, sparsely inhabited]
-
A.
residenceStatus
Indicates the type or condition of an entity’s living arrangement or place of residence in relation to a specified location.
-
B.
stateInhabited
Indicates that a particular state is (or was) lived in or occupied by a specified entity.
-
C.
residencyStatus
Indicates the legal or official residential classification of an entity within a particular jurisdiction or context.
-
D.
habitationStatusOfIsland
chosen
Indicates whether an island is inhabited, uninhabited, or otherwise characterized by a particular habitation status.
-
E.
habitation
Indicates that one entity serves as the dwelling place, residence, or living environment for 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_69ef5205fc808190ad3efc5525b8e6d6 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f62cdb62608190a8e1c84a631de5ce |
completed | May 2, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 12:32 p.m.