Triple
T21618986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basel SBB railway station |
E533523
|
entity |
| Predicate | hasIATACode |
P2569
|
FINISHED |
| Object | ZDH |
E533523
|
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: ZDH | Statement: [Basel SBB railway station, hasIATACode, ZDH]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ZDH Context triple: [Basel SBB railway station, hasIATACode, ZDH]
-
A.
ZDH
chosen
ZDH is the IATA station code for Basel SBB, the main Swiss railway station in Basel that connects major national and international train services.
-
B.
ZLDH
ZLDH is the ICAO airport code for Dunhuang Mogao International Airport in Gansu Province, China.
-
C.
QDH
QDH is the IATA station code used to identify Ashford International railway station in Kent, England.
-
D.
ZAH
ZAH is the IATA airport code for Zahedan International Airport in Zahedan, Iran.
-
E.
DZG
DZG is the vehicle registration code assigned to cars registered in the Bogatynia area of Poland.
- 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_69e0c464fba881908d0ff2ac80511ce1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef3bad094c8190879d4aef7988254a |
completed | April 27, 2026, 10:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09fd43e18881909d7ae551efe1cbe5 |
completed | May 17, 2026, 5:39 p.m. |
Created at: April 16, 2026, 6:34 p.m.