Triple
T23034781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VGHS |
E573563
|
entity |
| Predicate | hasTerminal |
P182
|
FINISHED |
| Object |
Terminal 1
Terminal 1 is a primary passenger terminal facility at VGHS airport, handling check-in, security, boarding, and arrivals operations.
|
E727056
|
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: Terminal 1 | Statement: [VGHS, hasTerminal, Terminal 1]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terminal 1 Context triple: [VGHS, hasTerminal, Terminal 1]
-
A.
Terminal 1
Terminal 1 is one of the main passenger terminals at Nice Côte d’Azur Airport, serving a variety of international and domestic flights on the French Riviera.
-
B.
Terminal 1
Terminal 1 is a major domestic passenger terminal at Melbourne Airport primarily serving Australian airlines and internal flights.
-
C.
Terminal 1
Terminal 1 is one of the passenger terminals at Mehrabad International Airport in Tehran, Iran, serving domestic air traffic.
-
D.
Terminal 1
Terminal 1 is a main passenger terminal at Birmingham Airport in the United Kingdom, handling check-in, security, departures, and arrivals for various domestic and international flights.
-
E.
Terminal 1
Terminal 1 is a passenger terminal at Chaudhary Charan Singh International Airport in Lucknow, India, serving as one of the airport’s main facilities for handling air travelers.
- 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: Terminal 1 Triple: [VGHS, hasTerminal, Terminal 1]
Generated description
Terminal 1 is a primary passenger terminal facility at VGHS airport, handling check-in, security, boarding, and arrivals operations.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Terminal 1 Target entity description: Terminal 1 is a primary passenger terminal facility at VGHS airport, handling check-in, security, boarding, and arrivals operations.
-
A.
Terminal 1
chosen
Terminal 1 is a primary passenger terminal facility at an airport, housing check-in, security, boarding gates, and various traveler services.
-
B.
Terminal 1
Terminal 1 is one of the main passenger terminals at Hamburg Airport, serving as a hub for check-in, security, and boarding operations.
-
C.
Terminal 1
Terminal 1 is one of the main passenger terminals at Zurich Airport, handling check-in, security, and boarding for a variety of international and domestic flights.
-
D.
Terminal 1
Terminal 1 is one of the main passenger terminals at Stuttgart Airport, handling check-in, security, and boarding operations for various airlines.
-
E.
Terminal 1
Terminal 1 is a passenger terminal at Lyon–Saint-Exupéry Airport that handles check-in, security, boarding, and arrivals for a portion of the airport’s commercial flights.
- F. None of above.
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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18483e5848190977b1bdb1b83d187 |
completed | April 29, 2026, 4:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0bf2b715e881909e1ee36eeb76ba18 |
completed | May 19, 2026, 5:18 a.m. |
| NEDg | Description generation | batch_6a0bfbd327148190b0717c8c35d85228 |
completed | May 19, 2026, 5:57 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0bfccedf2c8190833df43ea2c294ca |
completed | May 19, 2026, 6:01 a.m. |
Created at: April 17, 2026, 3:53 p.m.