Triple
T10103273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Galunggung |
E216254
|
entity |
| Predicate | airTrafficImpact |
P49069
|
FINISHED |
| Object | disrupted regional air traffic in 1982 |
—
|
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: disrupted regional air traffic in 1982 | Statement: [Galunggung, airTrafficImpact, disrupted regional air traffic in 1982]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airTrafficImpact Context triple: [Galunggung, airTrafficImpact, disrupted regional air traffic in 1982]
-
A.
affectsAirTraffic
chosen
Indicates that one entity causes changes or disruptions to the normal flow, safety, or management of air traffic.
-
B.
airTraffic
Indicates the movement and flow of aircraft through airspace, including their routes, density, and interactions while in flight.
-
C.
transportationImpact
Indicates how one entity’s transportation-related activities or characteristics affect another entity or the surrounding environment.
-
D.
passengerTraffic
Indicates the flow or volume of passengers moving through or using a particular transport service, route, or facility.
-
E.
aircraftImpact
Indicates that an aircraft collides with or crashes into a target or surface, causing an impact event.
- 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_69ca83d039f08190b9d10363221c69fb |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd09af07c819099774af46ebf62d7 |
completed | April 2, 2026, 2:12 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9b853c8190a2af993ce9b21309 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:03 p.m.