Triple
T14753581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | City Thameslink station |
E346674
|
entity |
| Predicate | stationCode |
P1289
|
FINISHED |
| Object | CTK |
E654859
|
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: CTK | Statement: [City Thameslink station, stationCode, CTK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CTK Context triple: [City Thameslink station, stationCode, CTK]
-
A.
CTK
chosen
CTK is the National Rail station code for City Thameslink, a central London railway station on the Thameslink route.
-
B.
TCK
TCK is a well-known horse racing track in Tokyo, Japan, officially known as Ohi Racecourse.
-
C.
TCK
TCK is a suite of tests, tools, and documentation used to verify that a technology implementation complies with a specific Java or Jakarta EE specification.
-
D.
KCK
KCK is an umbrella organization that unites various Kurdish political and militant groups, including the PKK, under a shared ideological and administrative framework.
-
E.
Tk
Tk is a cross-platform graphical user interface (GUI) toolkit commonly used with the Tcl scripting language to build windowed applications.
- 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_69d822e8896c819091169882f9b20486 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec7d59df08190a86da5048358bd6e |
completed | April 14, 2026, 11:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdfb9c725881908004368772fa528d |
completed | May 8, 2026, 3:05 p.m. |
Created at: April 10, 2026, 1:30 a.m.