Triple
T1994661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geneva Airport railway station |
E43330
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object | GVA |
E41842
|
NE 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: GVA | Statement: [Geneva Airport railway station, hasStationCode, GVA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GVA Context triple: [Geneva Airport railway station, hasStationCode, GVA]
-
A.
GVA
chosen
GVA is the IATA airport code for Geneva Airport, the international airport serving Geneva, Switzerland and the surrounding region.
-
B.
GVB
GVB is Amsterdam’s primary public transport company, operating the city’s trams, buses, metro, and ferries.
-
C.
GA
GA is the official two-letter United States Postal Service abbreviation for the state of Georgia.
-
D.
GA
GA is the commonly used abbreviation for the United Nations General Assembly, the main deliberative body of the UN where all member states are represented.
-
E.
GA
GA is the IATA airline designator for Garuda Indonesia, the national flag carrier of Indonesia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88714cf2c819081644be450b8356e |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8640f30819080322bddb85881f1 |
completed | March 7, 2026, 5:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae033c6cf88190acf6418f0d784914 |
completed | March 8, 2026, 11:16 p.m. |
Created at: March 4, 2026, 7:37 p.m.