Triple
T20725343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line 29 |
E509419
|
entity |
| Predicate | hasRollingStockType |
P1305
|
FINISHED |
| Object |
X15p EMU
The X15p EMU is an electric multiple unit train used for passenger services on Line 29.
|
E1446976
|
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: X15p EMU | Statement: [Line 29, hasRollingStockType, X15p EMU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: X15p EMU Context triple: [Line 29, hasRollingStockType, X15p EMU]
-
A.
X10p EMU
X10p EMU is a class of electric multiple unit trains used on Stockholm’s narrow-gauge Roslagsbanan commuter rail network.
-
B.
X60 EMU
The X60 EMU is a modern electric multiple unit train used for high-capacity commuter services in the Stockholm region.
-
C.
TX-1000 series EMU
The TX-1000 series EMU is a Japanese electric multiple unit train type operated on the Tsukuba Express line, designed for high-frequency commuter services in the Tokyo metropolitan area.
-
D.
Z 5600 EMU
The Z 5600 EMU is a class of French electric multiple unit trains built for suburban commuter services around Paris, notably operating on the RER network.
-
E.
X-Car trains
X-Car trains are a type of roller coaster train design known for their open, floorless seating and over-the-shoulder lap bar restraints that enhance riders’ sense of exposure and freedom.
- 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: X15p EMU Triple: [Line 29, hasRollingStockType, X15p EMU]
Generated description
The X15p EMU is an electric multiple unit train used for passenger services on Line 29.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: X15p EMU Target entity description: The X15p EMU is an electric multiple unit train used for passenger services on Line 29.
-
A.
X10p EMU
X10p EMU is a class of electric multiple unit trains used on Stockholm’s narrow-gauge Roslagsbanan commuter rail network.
-
B.
X60 EMU
The X60 EMU is a modern electric multiple unit train used for high-capacity commuter services in the Stockholm region.
-
C.
TX-1000 series EMU
The TX-1000 series EMU is a Japanese electric multiple unit train type operated on the Tsukuba Express line, designed for high-frequency commuter services in the Tokyo metropolitan area.
-
D.
Z 5600 EMU
The Z 5600 EMU is a class of French electric multiple unit trains built for suburban commuter services around Paris, notably operating on the RER network.
-
E.
X-Car trains
X-Car trains are a type of roller coaster train design known for their open, floorless seating and over-the-shoulder lap bar restraints that enhance riders’ sense of exposure and freedom.
- 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_69e0b4c4cc648190b45fda6e2b20af56 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1e7aabc819084f9e9fd45e877fd |
completed | April 21, 2026, 12:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08e05b8d6081908bc76627caf05188 |
completed | May 16, 2026, 9:23 p.m. |
| NEDg | Description generation | batch_6a08e13ca768819084c58419e058b111 |
completed | May 16, 2026, 9:27 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08e1e759ec8190a305662f220a1826 |
completed | May 16, 2026, 9:30 p.m. |
Created at: April 16, 2026, 12:29 p.m.