Triple
T16733953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seven Sisters Underground station |
E406668
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object | SVS |
E1230730
|
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: SVS | Statement: [Seven Sisters Underground station, hasStationCode, SVS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SVS Context triple: [Seven Sisters Underground station, hasStationCode, SVS]
-
A.
SVS
SVS is a professional medical society representing vascular surgeons and advancing the science, education, and practice of vascular surgery.
-
B.
SVS
chosen
SVS is the National Rail station code for Seven Sisters railway station in north London, England.
-
C.
SVJ
SVJ is the three-letter IATA airport code for Svolvær Airport, Helle in Norway.
-
D.
sva
sva is the ISO 639-3 code for the Svan language, a Kartvelian language spoken by the Svan people in the Svaneti region of northwestern Georgia.
-
E.
VSI
VSI is the commonly used abbreviation for the "Very Short Introductions" series of concise, authoritative books published by Oxford University Press on a wide range of subjects.
- 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_69d8838ffb088190a0b11149929006bf |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e39c38c9cc8190a3220cc3684388dc |
completed | April 18, 2026, 2:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00a519a89081909456bb6fc25d9234 |
completed | May 10, 2026, 3:32 p.m. |
Created at: April 10, 2026, 5:20 a.m.