Triple
T18972895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AT |
E464216
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object |
AT Metro
AT Metro is the public transport network brand for Auckland, New Zealand, covering bus, train, and ferry services managed by Auckland Transport.
|
E1352541
|
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: AT Metro | Statement: [AT, brand, AT Metro]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AT Metro Context triple: [AT, brand, AT Metro]
-
A.
Airport Metro
Airport Metro is a key Chennai Metro station serving Chennai International Airport and connecting air travelers to the city’s rapid transit network.
-
B.
METRO
METRO is the public-facing brand name used by Metro Transit for its network of buses, trains, and other mass transportation services.
-
C.
NFTA Metro
NFTA Metro is the public transit division serving the Buffalo–Niagara region in New York, operating local buses and light rail services.
-
D.
Metros
Metros is the nickname historically used for the MetroStars, the former Major League Soccer team now known as the New York Red Bulls.
-
E.
Premetro
Premetro is a light rail or tramway feeder line that connects outlying neighborhoods to the main Buenos Aires Subte (subway) network.
- 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: AT Metro Triple: [AT, brand, AT Metro]
Generated description
AT Metro is the public transport network brand for Auckland, New Zealand, covering bus, train, and ferry services managed by Auckland Transport.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: AT Metro Target entity description: AT Metro is the public transport network brand for Auckland, New Zealand, covering bus, train, and ferry services managed by Auckland Transport.
-
A.
Airport Metro
Airport Metro is a key Chennai Metro station serving Chennai International Airport and connecting air travelers to the city’s rapid transit network.
-
B.
METRO
METRO is the public-facing brand name used by Metro Transit for its network of buses, trains, and other mass transportation services.
-
C.
NFTA Metro
NFTA Metro is the public transit division serving the Buffalo–Niagara region in New York, operating local buses and light rail services.
-
D.
Metros
Metros is the nickname historically used for the MetroStars, the former Major League Soccer team now known as the New York Red Bulls.
-
E.
Premetro
Premetro is a light rail or tramway feeder line that connects outlying neighborhoods to the main Buenos Aires Subte (subway) network.
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d61cb3ac8190bfe29104166fa090 |
completed | April 20, 2026, 7:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05ad3b777c8190af377e88f0534e80 |
completed | May 14, 2026, 11:08 a.m. |
| NEDg | Description generation | batch_6a05afeed9188190b7a7ed4ae443dc2d |
completed | May 14, 2026, 11:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05b05c56048190a8a5b5aa4bfc6431 |
completed | May 14, 2026, 11:22 a.m. |
Created at: April 10, 2026, noon