Triple
T32372893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peggau |
E827193
|
entity |
| Predicate | stateCodeISO |
P20781
|
FINISHED |
| Object | AT-6 |
—
|
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: AT-6 | Statement: [Peggau, stateCodeISO, AT-6]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stateCodeISO Context triple: [Peggau, stateCodeISO, AT-6]
-
A.
icaoStateCode
Indicates the association between an entity (such as an aircraft, airline, or airport) and the ICAO-assigned state or country code under whose jurisdiction it falls.
-
B.
stateSubdivisionCode
chosen
Indicates the standardized code that identifies a specific subdivision (such as a state, province, or region) within a larger country or territory.
-
C.
stateOrTerritory
Indicates that one entity is a state or territory that is politically or administratively associated with another entity.
-
D.
provinceState
Indicates that one entity is a province or state that is administratively contained within or associated with another, typically larger, territorial entity.
-
E.
usesISO3166-2Code
Indicates that an entity employs or references a subdivision identifier defined by the ISO 3166-2 standard.
- 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_69f349166d548190887b412fe908e2f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fdbaa226708190b8ed96e93aad38de |
completed | May 8, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_69fdb58b07e48190837e00966de050d4 |
completed | May 8, 2026, 10:06 a.m. |
Created at: May 1, 2026, 12:50 a.m.