Triple

T34941742

Position	Surface form	Disambiguated ID	Type / Status
Subject	Flying Dutchman	`E1007739`	entity
Predicate	associatedCaptainName	`P182889`	FINISHED
Object	Van der Decken Van der Decken is the legendary, often cursed sea captain said to command the ghost ship known as the Flying Dutchman in maritime folklore.	`E2118332`	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: Van der Decken | Statement: [Flying Dutchman, associatedCaptainName, Van der Decken]

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: Van der Decken
Triple: [Flying Dutchman, associatedCaptainName, Van der Decken]

Generated description

Van der Decken is the legendary, often cursed sea captain said to command the ghost ship known as the Flying Dutchman in maritime folklore.

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

Target predicate: associatedCaptainName
Context triple: [Flying Dutchman, associatedCaptainName, Van der Decken]

A. captainInName
Indicates that an entity’s name or title explicitly includes the word “Captain.”
B. assistantCaptain
Indicates that one entity serves as the assistant or deputy to another entity who holds the role of captain.
C. teamCaptain
Indicates that one entity serves as the captain or designated leader of a particular team.
D. hasCaptainPortrayedBy
Indicates that the captain of an entity (e.g., a team, ship, or group) is portrayed or played by a specific person.
E. captainedByCharacter chosen
Indicates that an entity (such as a ship, team, or group) is led or commanded by a specific character serving as its captain.
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_69f76dc513fc819084a1ff52abbfa5bc`	completed	May 3, 2026, 3:46 p.m.
NER	Named-entity recognition	`batch_6a037c8c34f88190ace26f555827f23e`	completed	May 12, 2026, 7:16 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a37a8c1262881908e9d59e4f149ef7b`	completed	June 21, 2026, 9:02 a.m.
NEDg	Description generation	`batch_6a37aa4114108190a96aa42c2fb45353`	completed	June 21, 2026, 9:09 a.m.
NED2	Entity disambiguation (via description)	`batch_6a37aaf963788190b1b346e25439e105`	completed	June 21, 2026, 9:12 a.m.
PD	Predicate disambiguation	`batch_6a0379ff1ba081908eda86acefcf69fb`	completed	May 12, 2026, 7:05 p.m.

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