Triple
T17731419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Douglas DC-7 |
E442593
|
entity |
| Predicate | ICAOTypeDesignator |
P16898
|
FINISHED |
| Object |
DC7
DC7 is the ICAO aircraft type designator for the Douglas DC-7, a four‑engine propeller-driven airliner introduced in the 1950s for long-range commercial flights.
|
E1285020
|
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: DC7 | Statement: [Douglas DC-7, ICAOTypeDesignator, DC7]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DC7 Context triple: [Douglas DC-7, ICAOTypeDesignator, DC7]
-
A.
DC6
DC6 is the ISO code designating the Namakwa District Municipality in South Africa’s Northern Cape province.
-
B.
DCC
DCC is a public community college located in Dutchess County, New York, offering two-year degree and certificate programs.
-
C.
DCC
DCC (Direct Client-to-Client) is an IRC protocol extension that enables users to establish direct connections for private chats and file transfers outside the main IRC server.
-
D.
D train
The D train is a major New York City Subway service that runs as an express route through Manhattan and the Bronx, connecting key neighborhoods across multiple boroughs.
-
E.
DC3
DC3 is a public community college in Dodge City, Kansas, offering two-year academic and technical programs.
- 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: DC7 Triple: [Douglas DC-7, ICAOTypeDesignator, DC7]
Generated description
DC7 is the ICAO aircraft type designator for the Douglas DC-7, a four‑engine propeller-driven airliner introduced in the 1950s for long-range commercial flights.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: DC7 Target entity description: DC7 is the ICAO aircraft type designator for the Douglas DC-7, a four‑engine propeller-driven airliner introduced in the 1950s for long-range commercial flights.
-
A.
DC6
DC6 is the ISO code designating the Namakwa District Municipality in South Africa’s Northern Cape province.
-
B.
DCC
DCC is a public community college located in Dutchess County, New York, offering two-year degree and certificate programs.
-
C.
DCC
DCC (Direct Client-to-Client) is an IRC protocol extension that enables users to establish direct connections for private chats and file transfers outside the main IRC server.
-
D.
D train
The D train is a major New York City Subway service that runs as an express route through Manhattan and the Bronx, connecting key neighborhoods across multiple boroughs.
-
E.
DC3
DC3 is a public community college in Dodge City, Kansas, offering two-year academic and technical programs.
- 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_69d8b9ec79688190b86bdcef85a7b3aa |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e478e69f288190900027641952f198 |
completed | April 19, 2026, 6:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0242f577ac8190bc6c258ed79c0f3f |
completed | May 11, 2026, 8:58 p.m. |
| NEDg | Description generation | batch_6a024432dae081908718b4d9fa156858 |
completed | May 11, 2026, 9:03 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0244ad73388190b5b99ccbbd357d77 |
completed | May 11, 2026, 9:05 p.m. |
Created at: April 10, 2026, 10:08 a.m.