Triple

T26901941

Position	Surface form	Disambiguated ID	Type / Status
Subject	Palace of the Heavenly King (Taiping Heavenly Kingdom)	`E678054`	entity
Predicate	cityDuringTaipingRule	`P161985`	FINISHED
Object	Tianjing Tianjing was the capital city of the Taiping Heavenly Kingdom, serving as the political and military center of the mid-19th-century Taiping Rebellion in China.	`E1758824`	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: Tianjing | Statement: [Palace of the Heavenly King (Taiping Heavenly Kingdom), cityDuringTaipingRule, Tianjing]

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: Tianjing
Triple: [Palace of the Heavenly King (Taiping Heavenly Kingdom), cityDuringTaipingRule, Tianjing]

Generated description

Tianjing was the capital city of the Taiping Heavenly Kingdom, serving as the political and military center of the mid-19th-century Taiping Rebellion in China.

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

Target predicate: cityDuringTaipingRule
Context triple: [Palace of the Heavenly King (Taiping Heavenly Kingdom), cityDuringTaipingRule, Tianjing]

A. administrativeStatusDuringJapaneseRule
Indicates the administrative status or classification an entity held under Japanese colonial rule during the specified period.
B. cityDuringImperialPeriod
Indicates that a location functioned as a city during a specified imperial or empire-dominated historical period.
C. capitalDuringBritishRule
Indicates that a place served as the capital of a region or polity specifically during the period of British rule.
D. compiledUnderDynasty
Indicates that a work or document was compiled during the reign or period of a specific dynasty.
E. capturedDuringReignOf
Indicates that one entity was captured while another entity was in power or ruling (i.e., during the time span of that entity’s reign).
F. None of above. chosen

Provenance (7 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_69eee9befee48190a26f214faa867be7`	completed	April 27, 2026, 4:44 a.m.
NER	Named-entity recognition	`batch_69f62081136c81909de8090b1d6c1ac5`	completed	May 2, 2026, 4:04 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a1247e50de88190aba0384aa5c30cfc`	completed	May 24, 2026, 12:35 a.m.
NEDg	Description generation	`batch_6a1249973fe48190ac773c774941b397`	completed	May 24, 2026, 12:43 a.m.
NED2	Entity disambiguation (via description)	`batch_6a124a50c12c8190a37b7286847e7b12`	completed	May 24, 2026, 12:46 a.m.
PD	Predicate disambiguation	`batch_69f61b3d23f481908dfec27adace900a`	completed	May 2, 2026, 3:41 p.m.
PDg	Predicate description generation	`batch_69f61fd5442081908ca677a9c81dcb3f`	completed	May 2, 2026, 4:01 p.m.

Created at: April 27, 2026, 5:51 a.m.