Triple

T23600248

Position	Surface form	Disambiguated ID	Type / Status
Subject	Revenge (English galleon)	`E582729`	entity
Predicate	constructionPlace	`P14101`	FINISHED
Object	Plymouth shipyards Plymouth shipyards were prominent English naval dockyards in Plymouth, Devon, known for building significant warships during the age of sail.	`E1593246`	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: Plymouth shipyards | Statement: [Revenge (English galleon), constructionPlace, Plymouth shipyards]

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: Plymouth shipyards
Triple: [Revenge (English galleon), constructionPlace, Plymouth shipyards]

Generated description

Plymouth shipyards were prominent English naval dockyards in Plymouth, Devon, known for building significant warships during the age of sail.

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

Target predicate: constructionPlace
Context triple: [Revenge (English galleon), constructionPlace, Plymouth shipyards]

A. constructionSite
Indicates that an entity is a location or area where construction work is actively taking place or is planned to occur.
B. buildingInvolved
Indicates that a particular building participates in, is affected by, or is otherwise relevant to the specified event or relationship.
C. placeBuilt chosen
Indicates that a structure or facility was constructed at a specific location.
D. constructionBase
Indicates that one entity serves as the foundational structure or base upon which another entity is constructed or built.
E. constructionDirection
Indicates the orientation or path along which a structure is built or assembled.
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_69e248faa2788190abb1581742daa6aa`	completed	April 17, 2026, 2:51 p.m.
NER	Named-entity recognition	`batch_69f1b0936f588190aead4419aedfcb0e`	completed	April 29, 2026, 7:17 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a0f4584e1a881909542ccd283d9db76`	completed	May 21, 2026, 5:48 p.m.
NEDg	Description generation	`batch_6a0f46d5885c819098231e2178e6606e`	completed	May 21, 2026, 5:54 p.m.
NED2	Entity disambiguation (via description)	`batch_6a0f47c1651c8190bd49eb119f7525ec`	completed	May 21, 2026, 5:58 p.m.
PD	Predicate disambiguation	`batch_69f118c96a0081908a8ac98ef7e7e60c`	completed	April 28, 2026, 8:30 p.m.

Created at: April 17, 2026, 6:43 p.m.