Triple

T26834249

Position	Surface form	Disambiguated ID	Type / Status
Subject	Tatopani–Zhangmu border crossing	`E675583`	entity
Predicate	customsPost	`P7676`	FINISHED
Object	Tatopani customs office Tatopani customs office is a Nepalese border customs facility that handles immigration and trade processing at the Tatopani–Zhangmu crossing between Nepal and China.	`E1745371`	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: Tatopani customs office | Statement: [Tatopani–Zhangmu border crossing, customsPost, Tatopani customs office]

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: Tatopani customs office
Triple: [Tatopani–Zhangmu border crossing, customsPost, Tatopani customs office]

Generated description

Tatopani customs office is a Nepalese border customs facility that handles immigration and trade processing at the Tatopani–Zhangmu crossing between Nepal and China.

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

Target predicate: customsPost
Context triple: [Tatopani–Zhangmu border crossing, customsPost, Tatopani customs office]

A. customs chosen
Indicates that an entity is responsible for regulating, inspecting, or processing goods and people as they cross a border for legal and tax purposes.
B. customsClearance
Indicates the process by which goods or shipments are reviewed, processed, and officially approved by customs authorities for entry into or exit from a country.
C. customsAssociated
Indicates that certain cultural or social customs are connected with, practiced by, or characteristic of a particular entity.
D. customsInstrument
Indicates that one entity serves as a tool, method, or means used by customs authorities to perform or facilitate a customs-related action involving another entity.
E. customsRegime
Indicates the specific customs treatment or regulatory framework under which goods are imported, exported, or stored.
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_69eee9b776448190993a60b67fcc9545`	completed	April 27, 2026, 4:44 a.m.
NER	Named-entity recognition	`batch_69f62d53ad58819080c5227c7a729d15`	completed	May 2, 2026, 4:58 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a121341e99c8190a395c02926591866`	completed	May 23, 2026, 8:51 p.m.
NEDg	Description generation	`batch_6a12167fa7148190a6e3ce72bde43f93`	completed	May 23, 2026, 9:05 p.m.
NED2	Entity disambiguation (via description)	`batch_6a121725f8d48190bbf8a15cfd332ee0`	completed	May 23, 2026, 9:07 p.m.
PD	Predicate disambiguation	`batch_69f62c15952881908a5ea0c25904afec`	completed	May 2, 2026, 4:53 p.m.

Created at: April 27, 2026, 5:03 a.m.