Triple
T19736377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U-Bahn station Friedrich-Wilhelm-Platz |
E473993
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object |
FW
FW is the station code for the Berlin U-Bahn station Friedrich-Wilhelm-Platz.
|
E1392302
|
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: FW | Statement: [U-Bahn station Friedrich-Wilhelm-Platz, hasStationCode, FW]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FW Context triple: [U-Bahn station Friedrich-Wilhelm-Platz, hasStationCode, FW]
-
A.
FW
FW is the IATA airline designator assigned to the Japanese regional carrier Ibex Airlines.
-
B.
FW
FW refers to the Free Voters (Freie Wähler), a German political association and party known for its strong local-government focus and presence in Bavarian municipal and regional politics.
-
C.
FW
FW is the designation used for the series of Formula One racing car chassis developed and raced by the Williams Grand Prix Engineering team.
-
D.
WF
WF is the common abbreviation for Wikifunctions, a Wikimedia project aimed at creating a collaborative catalog of reusable functions.
-
E.
WF
WF is the common abbreviation for Windows Workflow Foundation, a Microsoft technology for building workflow-enabled applications within the .NET framework.
- 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: FW Triple: [U-Bahn station Friedrich-Wilhelm-Platz, hasStationCode, FW]
Generated description
FW is the station code for the Berlin U-Bahn station Friedrich-Wilhelm-Platz.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: FW Target entity description: FW is the station code for the Berlin U-Bahn station Friedrich-Wilhelm-Platz.
-
A.
FW
FW is the IATA airline designator assigned to the Japanese regional carrier Ibex Airlines.
-
B.
FW
FW refers to the Free Voters (Freie Wähler), a German political association and party known for its strong local-government focus and presence in Bavarian municipal and regional politics.
-
C.
FW
FW is the designation used for the series of Formula One racing car chassis developed and raced by the Williams Grand Prix Engineering team.
-
D.
WF
WF is the common abbreviation for Wikifunctions, a Wikimedia project aimed at creating a collaborative catalog of reusable functions.
-
E.
WF
WF is the common abbreviation for Windows Workflow Foundation, a Microsoft technology for building workflow-enabled applications within the .NET framework.
- 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6515ddea881909ea831b7bc16d934 |
completed | April 20, 2026, 4:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07b4f944108190b63432ef6d0eb984 |
completed | May 16, 2026, 12:06 a.m. |
| NEDg | Description generation | batch_6a07b5c7a0348190b06f5300c89f0548 |
completed | May 16, 2026, 12:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07b655722c8190be1b30d1e276c580 |
completed | May 16, 2026, 12:12 a.m. |
Created at: April 10, 2026, 1:47 p.m.