Triple
T3984447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BMT Broadway Line |
E86837
|
entity |
| Predicate | formerServices |
P43939
|
FINISHED |
| Object |
EE
The EE was a former New York City Subway service that operated on the BMT Broadway Line, primarily providing local service in Manhattan and Queens before being discontinued.
|
E404848
|
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: EE | Statement: [BMT Broadway Line, formerServices, EE]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: EE Context triple: [BMT Broadway Line, formerServices, EE]
-
A.
EE
EE is a major British mobile network operator and internet service provider known for its extensive 4G and 5G coverage across the UK.
-
B.
EEE
EEE is the internal BBC production code assigned to the Doctor Who serial "Terror of the Autons."
-
C.
ECE
ECE is the Explicit Congestion Experienced flag used in IP and TCP headers to indicate network congestion without dropping packets, as defined in RFC 3168’s ECN mechanism.
-
D.
EET
EET is a time zone used in parts of Eastern Europe and the Eastern Mediterranean, typically two hours ahead of Coordinated Universal Time (UTC+2).
-
E.
BSEE
BSEE is a U.S. federal agency within the Department of the Interior responsible for overseeing safety and environmental protection in offshore oil and gas operations.
- 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: EE Triple: [BMT Broadway Line, formerServices, EE]
Generated description
The EE was a former New York City Subway service that operated on the BMT Broadway Line, primarily providing local service in Manhattan and Queens before being discontinued.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: EE Target entity description: The EE was a former New York City Subway service that operated on the BMT Broadway Line, primarily providing local service in Manhattan and Queens before being discontinued.
-
A.
EE
EE is a major British mobile network operator and internet service provider known for its extensive 4G and 5G coverage across the UK.
-
B.
EEE
EEE is the internal BBC production code assigned to the Doctor Who serial "Terror of the Autons."
-
C.
ECE
ECE is the Explicit Congestion Experienced flag used in IP and TCP headers to indicate network congestion without dropping packets, as defined in RFC 3168’s ECN mechanism.
-
D.
EET
EET is a time zone used in parts of Eastern Europe and the Eastern Mediterranean, typically two hours ahead of Coordinated Universal Time (UTC+2).
-
E.
BSEE
BSEE is a U.S. federal agency within the Department of the Interior responsible for overseeing safety and environmental protection in offshore oil and gas operations.
- 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_69aed93fd9d4819085d3b2137d2346cb |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0197a0a0819085d746f51c7fc51b |
completed | March 9, 2026, 5:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b540284d548190821d37b68974a2d2 |
completed | March 14, 2026, 11:02 a.m. |
| NEDg | Description generation | batch_69b54126234c8190990cf6df84a83e92 |
completed | March 14, 2026, 11:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5458d736481908ca826fa4fd01b8c |
completed | March 14, 2026, 11:25 a.m. |
Created at: March 9, 2026, 3:33 p.m.