Triple

T35534199

Position	Surface form	Disambiguated ID	Type / Status
Subject	Croatian A6 motorway	`E1026883`	entity
Predicate	hasNotableViaduct	`P17088`	FINISHED
Object	Zečeve Drage Viaduct Zečeve Drage Viaduct is a major Croatian highway bridge known for its large concrete spans and role in carrying traffic through the mountainous route of the A6 motorway between Zagreb and Rijeka.	`E2146840`	NE FINISHED

How this triple was built (3 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: Zečeve Drage Viaduct | Statement: [Croatian A6 motorway, hasNotableViaduct, Zečeve Drage Viaduct]

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: Zečeve Drage Viaduct
Triple: [Croatian A6 motorway, hasNotableViaduct, Zečeve Drage Viaduct]

Generated description

Zečeve Drage Viaduct is a major Croatian highway bridge known for its large concrete spans and role in carrying traffic through the mountainous route of the A6 motorway between Zagreb and Rijeka.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: hasNotableViaduct
Context triple: [Croatian A6 motorway, hasNotableViaduct, Zečeve Drage Viaduct]

A. hasViaduct chosen
Indicates that one entity possesses, includes, or is connected by a viaduct in relation to another entity.
B. numberOfViaducts
Indicates the count of viaduct structures associated with or present in a given context or entity.
C. hasViaductSections
Indicates that something includes or is composed of one or more viaduct sections as part of its structure or layout.
D. hasPassengerBridge
Indicates that one entity is connected to another by a bridge or walkway specifically designed for passengers to move between them.
E. hasMajorBridge
Indicates that one entity possesses or includes a primary or significant bridge associated with it.
F. None of above.

Provenance (6 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_69f76dff7e508190b28ceeee770dce23`	completed	May 3, 2026, 3:47 p.m.
NER	Named-entity recognition	`batch_6a037c8d06cc8190ab6a5e18d9d2571e`	completed	May 12, 2026, 7:16 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a3852e9b2f481908ddf999b98bdf356`	completed	June 21, 2026, 9:08 p.m.
NEDg	Description generation	`batch_6a3856c969348190afc2ec73fd8d8f28`	completed	June 21, 2026, 9:25 p.m.
NED2	Entity disambiguation (via description)	`batch_6a385720d3ac8190977a17e2ea0f4def`	completed	June 21, 2026, 9:26 p.m.
PD	Predicate disambiguation	`batch_6a037a04d8348190a4819666eab42c9b`	completed	May 12, 2026, 7:05 p.m.

Created at: May 3, 2026, 4:04 p.m.