Triple

T37370734

Position	Surface form	Disambiguated ID	Type / Status
Subject	Battle of Narva	`E927834`	entity
Predicate	hasDefensiveForce	`P200567`	FINISHED
Object	Swedish garrison in Narva The Swedish garrison in Narva was the fortified Swedish military force stationed in the city of Narva, crucial in defending it during the Great Northern War.	`E2224612`	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: Swedish garrison in Narva | Statement: [Battle of Narva, hasDefensiveForce, Swedish garrison in Narva]

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: Swedish garrison in Narva
Triple: [Battle of Narva, hasDefensiveForce, Swedish garrison in Narva]

Generated description

The Swedish garrison in Narva was the fortified Swedish military force stationed in the city of Narva, crucial in defending it during the Great Northern War.

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

Target predicate: hasDefensiveForce
Context triple: [Battle of Narva, hasDefensiveForce, Swedish garrison in Narva]

A. hasDefensiveType
Indicates that an entity possesses or is associated with a particular defensive category, attribute, or capability used for protection.
B. hasDefensiveWork
Indicates that an entity possesses or is associated with a work focused on defense or protective functions.
C. hasDefensivePositions
Indicates that an entity possesses or controls locations, structures, or arrangements specifically organized for defense against potential threats or attacks.
D. hasDefenderStrength
Indicates that an entity possesses a certain level or measure of defensive capability or protective power.
E. hasDefenseStrategy
Indicates that an entity employs or is associated with a particular plan or set of measures designed to protect against threats or attacks.
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_69f76eb820248190a5c395ca50ad002a`	completed	May 3, 2026, 3:50 p.m.
NER	Named-entity recognition	`batch_69ff965f9be48190b015b788207be676`	completed	May 9, 2026, 8:17 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a406cef5ec08190ab27ee99af9953ab`	completed	June 28, 2026, 12:38 a.m.
NEDg	Description generation	`batch_6a406e564c1881908e4f7af6ef6e5513`	completed	June 28, 2026, 12:44 a.m.
NED2	Entity disambiguation (via description)	`batch_6a4072845e408190b662e3edccf59fb3`	completed	June 28, 2026, 1:01 a.m.
PD	Predicate disambiguation	`batch_69ff95d3015c8190b9d293fe31b859c3`	completed	May 9, 2026, 8:15 p.m.
PDg	Predicate description generation	`batch_69ff965eef90819097499d1f0542378c`	completed	May 9, 2026, 8:17 p.m.

Created at: May 3, 2026, 4:16 p.m.