Triple

T37518635
Position Surface form Disambiguated ID Type / Status
Subject South Bend International Airport E932701 entity
Predicate hasRunway P105 FINISHED
Object Runway 9R/27L
Runway 9R/27L is a designated aircraft landing and takeoff strip at South Bend International Airport in Indiana, United States.
E957500 NE FINISHED

How this triple was built (2 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: Runway 9R/27L | Statement: [South Bend International Airport, hasRunway, Runway 9R/27L]
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: Runway 9R/27L
Triple: [South Bend International Airport, hasRunway, Runway 9R/27L]
Generated description
Runway 9R/27L is a designated aircraft landing and takeoff strip at South Bend International Airport in Indiana, United States.

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_69f76ec730988190b5aa4f9cb9afd518 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fba3ce1d308190ae4956ad45c33964 completed May 6, 2026, 8:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a4560c01e0881909be5002ca9b2707f completed July 1, 2026, 6:47 p.m.
NEDg Description generation batch_6a457025a6188190ac54821ae19cdf5d completed July 1, 2026, 7:53 p.m.
NED2 Entity disambiguation (via description) batch_6a45913132248190935a23be2ece2aa6 completed July 1, 2026, 10:14 p.m.
Created at: May 3, 2026, 4:17 p.m.