Triple
T22519946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gamla stan metro station |
E556746
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object |
Gst
Gst is the station code used to identify Gamla stan metro station in the Stockholm metro system.
|
E1540358
|
NE FINISHED |
How this triple was built (4 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: Gst | Statement: [Gamla stan metro station, hasStationCode, Gst]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gst Context triple: [Gamla stan metro station, hasStationCode, Gst]
-
A.
GStreamer
GStreamer is an open-source multimedia framework used to build complex audio and video processing pipelines across multiple platforms.
-
B.
GTS
GTS is a high-performance, sport-oriented variant of the Holden Monaro produced by Holden’s performance division.
-
C.
GTS
GTS is a performance-oriented trim designation used by Chrysler for sportier, upgraded versions of certain LeBaron models.
-
D.
GTS
GTS is an abbreviation commonly used for the Global Telecommunication System, an international network for exchanging meteorological data.
-
E.
Gobo
Gobo is a coastal city in Japan known for its fishing industry and location in Wakayama Prefecture on the Kii Peninsula.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Gst Triple: [Gamla stan metro station, hasStationCode, Gst]
Generated description
Gst is the station code used to identify Gamla stan metro station in the Stockholm metro system.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gst Target entity description: Gst is the station code used to identify Gamla stan metro station in the Stockholm metro system.
-
A.
GStreamer
GStreamer is an open-source multimedia framework used to build complex audio and video processing pipelines across multiple platforms.
-
B.
GTS
GTS is a high-performance, sport-oriented variant of the Holden Monaro produced by Holden’s performance division.
-
C.
GTS
GTS is a performance-oriented trim designation used by Chrysler for sportier, upgraded versions of certain LeBaron models.
-
D.
GTS
GTS is an abbreviation commonly used for the Global Telecommunication System, an international network for exchanging meteorological data.
-
E.
Gobo
Gobo is a coastal city in Japan known for its fishing industry and location in Wakayama Prefecture on the Kii Peninsula.
- F. None of above. chosen
Provenance (5 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_69e11e5657e881909f16ca58352c50da |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15e31f43c8190899f5e35b150fe85 |
completed | April 29, 2026, 1:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b17f44de48190a086900e1ca5cdc1 |
completed | May 18, 2026, 1:45 p.m. |
| NEDg | Description generation | batch_6a0b189b025c8190935d77837edac094 |
completed | May 18, 2026, 1:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b193a558c81909c8c8c8bd82f7bda |
completed | May 18, 2026, 1:50 p.m. |
Created at: April 16, 2026, 8:50 p.m.