Triple
T6473372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stadler Rail |
E146008
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object |
TANGO
TANGO is a family of modern light rail and tram vehicles produced by the Swiss rolling stock manufacturer Stadler Rail.
|
E595579
|
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: TANGO | Statement: [Stadler Rail, brand, TANGO]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TANGO Context triple: [Stadler Rail, brand, TANGO]
-
A.
tango
Tango is a passionate and dramatic partner dance and musical style that originated in the working-class neighborhoods of Buenos Aires and Montevideo in the late 19th century.
-
B.
Calera de Tango
Calera de Tango is a semi-rural commune and town in central Chile known for its agricultural activity and proximity to Santiago.
-
C.
Tanca
Tanca was a historical figure known primarily as the assassin of King Jayanegara of the Majapahit Kingdom in 14th-century Java.
-
D.
Libertango
"Libertango" is a famous tango nuevo composition by Ástor Piazzolla, widely recognized for its fusion of classical, jazz, and traditional Argentine tango elements.
-
E.
Tanza
Tanza is a coastal municipality in the province of Cavite in the Philippines, known for its historical significance and growing residential and industrial communities.
- 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: TANGO Triple: [Stadler Rail, brand, TANGO]
Generated description
TANGO is a family of modern light rail and tram vehicles produced by the Swiss rolling stock manufacturer Stadler Rail.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: TANGO Target entity description: TANGO is a family of modern light rail and tram vehicles produced by the Swiss rolling stock manufacturer Stadler Rail.
-
A.
tango
Tango is a passionate and dramatic partner dance and musical style that originated in the working-class neighborhoods of Buenos Aires and Montevideo in the late 19th century.
-
B.
Calera de Tango
Calera de Tango is a semi-rural commune and town in central Chile known for its agricultural activity and proximity to Santiago.
-
C.
Tanca
Tanca was a historical figure known primarily as the assassin of King Jayanegara of the Majapahit Kingdom in 14th-century Java.
-
D.
Libertango
"Libertango" is a famous tango nuevo composition by Ástor Piazzolla, widely recognized for its fusion of classical, jazz, and traditional Argentine tango elements.
-
E.
Tanza
Tanza is a coastal municipality in the province of Cavite in the Philippines, known for its historical significance and growing residential and industrial communities.
- 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_69c008fec7408190af7b146dc63d9750 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c06a32c0188190bcb3c35fc1d796a6 |
completed | March 22, 2026, 10:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c653a2b2508190a3691412f853ed6f |
completed | March 27, 2026, 9:53 a.m. |
| NEDg | Description generation | batch_69c6552b90848190961250b1e64595e1 |
completed | March 27, 2026, 10 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c655bce7548190b4c5661a7aaa77e1 |
completed | March 27, 2026, 10:02 a.m. |
Created at: March 22, 2026, 4:50 p.m.