Triple
T15465004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ditton Marsh |
E372008
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object | ESH |
E270080
|
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: ESH | Statement: [Ditton Marsh, hasStationCode, ESH]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ESH Context triple: [Ditton Marsh, hasStationCode, ESH]
-
A.
ESH
chosen
ESH is the IATA airport code for Shoreham-by-Sea airfield, a regional airport on the south coast of England.
-
B.
ESMD
ESMD is the former NASA directorate responsible for developing human and robotic exploration systems for missions beyond low Earth orbit.
-
C.
ELS
ELS is the abbreviation for the Existing Liabilities Scheme, a regulatory framework dealing with pre-existing financial or insurance obligations.
-
D.
ELS
ELS is a Soyuz launch complex at the Guiana Space Centre in French Guiana used for orbiting satellites and other payloads.
-
E.
ESHCC
ESHCC is a faculty of Erasmus University Rotterdam specializing in academic programs and research in history, culture, media, and communication.
- 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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f680cec8190836a5ec841dee224 |
completed | April 16, 2026, 1:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2d01a23c819095cf75b7d5a801a9 |
completed | May 9, 2026, 12:48 p.m. |
Created at: April 10, 2026, 3:33 a.m.