Triple
T15545605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waterloo railway station |
E370600
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object | WLO |
E563495
|
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: WLO | Statement: [Waterloo railway station, hasStationCode, WLO]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WLO Context triple: [Waterloo railway station, hasStationCode, WLO]
-
A.
WLO
chosen
WLO is the National Rail station code used to identify London Waterloo Underground station in the UK rail network.
-
B.
WNLO
WNLO is a major Chinese research institute specializing in optoelectronics and photonics, based in Wuhan.
-
C.
WLV
WLV is the National Rail station code for Wallasey Village railway station on the Wirral Line in Merseyside, England.
-
D.
WOB
WOB is the vehicle registration code used on license plates for cars registered in Wolfsburg, Germany.
-
E.
WL
WL is the station code for Lutherstadt Wittenberg railway station in Germany.
- 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_69d85cc521a08190921fb50319dddc34 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e0443410408190a249889edcd9c599 |
completed | April 16, 2026, 2:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff455a38188190a593c70be09d6103 |
completed | May 9, 2026, 2:31 p.m. |
Created at: April 10, 2026, 4:07 a.m.