Triple

T36595334

Position	Surface form	Disambiguated ID	Type / Status
Subject	Benguela Railway	`E902780`	entity
Predicate	rehabilitationContractor	`P126818`	FINISHED
Object	China Railway 20 Bureau Group China Railway 20 Bureau Group is a major Chinese state-owned construction and engineering company specializing in large-scale railway and infrastructure projects worldwide.	`E2191431`	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: China Railway 20 Bureau Group | Statement: [Benguela Railway, rehabilitationContractor, China Railway 20 Bureau Group]

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: China Railway 20 Bureau Group
Triple: [Benguela Railway, rehabilitationContractor, China Railway 20 Bureau Group]

Generated description

China Railway 20 Bureau Group is a major Chinese state-owned construction and engineering company specializing in large-scale railway and infrastructure projects worldwide.

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

Target predicate: rehabilitationContractor
Context triple: [Benguela Railway, rehabilitationContractor, China Railway 20 Bureau Group]

A. rehabilitationProject
Indicates that an entity is involved in a project aimed at restoring, improving, or returning something to a better or functional condition.
B. rehabilitationSupport
Indicates providing assistance, resources, or services that help an entity recover, restore function, or reintegrate after injury, illness, or adverse conditions.
C. rebuildContractor chosen
Indicates that an entity serves as the contractor responsible for rebuilding or reconstructing another entity (such as a structure, system, or asset).
D. rehabilitates
Indicates that one entity restores, reforms, or helps another entity return to a previous or improved functional, social, or legal state after damage, illness, or wrongdoing.
E. rehabilitationEvent
Indicates an event in which an entity undergoes a process of rehabilitation, such as recovery, restoration, or reintegration following damage, illness, or misconduct.
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_69f76e6592e88190bac4eb00a46e9df9`	completed	May 3, 2026, 3:48 p.m.
NER	Named-entity recognition	`batch_69f7c777e924819081a6634f549fe552`	completed	May 3, 2026, 10:08 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a39f922bfe48190a9f67a6f5cb07cc7`	completed	June 23, 2026, 3:10 a.m.
NEDg	Description generation	`batch_6a39fd045eb08190b571135a2c2ddd38`	completed	June 23, 2026, 3:27 a.m.
NED2	Entity disambiguation (via description)	`batch_6a3a0158bbcc8190bc983b8f0266774b`	completed	June 23, 2026, 3:45 a.m.
PD	Predicate disambiguation	`batch_69f7c477a4d481908f52e55b6688f60c`	completed	May 3, 2026, 9:56 p.m.

Created at: May 3, 2026, 4:11 p.m.