Triple
T17235420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Summerhill subway station |
E418344
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object | SU |
E280558
|
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: SU | Statement: [Summerhill subway station, hasStationCode, SU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SU Context triple: [Summerhill subway station, hasStationCode, SU]
-
A.
SU
SU was the two-letter country code used to represent the former Soviet Union in various international standards and systems.
-
B.
SU
SU is the vehicle registration code for the Rhein-Sieg-Kreis district in the German state of North Rhine-Westphalia.
-
C.
SU
SU is the IATA airline designator for Aeroflot, Russia’s flag carrier and largest airline.
-
D.
SU
chosen
SU is the station code used to identify Summerhill railway station.
-
E.
SU
SU is the commonly used abbreviation for Stockholm University, a major public research university in Stockholm, Sweden.
- 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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42dfb04e481909f4ee3ed31fffe10 |
completed | April 19, 2026, 1:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01676382388190ab82bd10bd53f59e |
completed | May 11, 2026, 5:21 a.m. |
Created at: April 10, 2026, 5:39 a.m.