Triple

T36556294

Position	Surface form	Disambiguated ID	Type / Status
Subject	Bay of Belfalas	`E901706`	entity
Predicate	nearbyHaven	`P61270`	FINISHED
Object	Havens of Umbar The Havens of Umbar are a notorious Corsair stronghold and seaport in J.R.R. Tolkien’s Middle-earth, long associated with seafaring raiders and enemies of Gondor.	`E2189566`	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: Havens of Umbar | Statement: [Bay of Belfalas, nearbyHaven, Havens of Umbar]

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: Havens of Umbar
Triple: [Bay of Belfalas, nearbyHaven, Havens of Umbar]

Generated description

The Havens of Umbar are a notorious Corsair stronghold and seaport in J.R.R. Tolkien’s Middle-earth, long associated with seafaring raiders and enemies of Gondor.

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

Target predicate: nearbyHaven
Context triple: [Bay of Belfalas, nearbyHaven, Havens of Umbar]

A. hasNearbyLodge
Indicates that one entity is located close to or in the vicinity of a lodge associated with another entity.
B. nearbyResortArea
Indicates that a resort area is located close to or within a short distance of a specified place or entity.
C. nearbyVenue
Indicates that one venue is located close to another venue in physical space.
D. nearbyUse
Indicates that one entity uses or operates another entity that is located nearby or in close physical proximity.
E. nearbyLocation chosen
Indicates that one location is situated close to another location in physical space.
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_69f76e634e9481908c9ba1b87ab87c26`	completed	May 3, 2026, 3:48 p.m.
NER	Named-entity recognition	`batch_69feecf1bb248190ba30f0bb1d22ee08`	completed	May 9, 2026, 8:14 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a39e6f034fc8190af0ebae6ade6f48b`	completed	June 23, 2026, 1:52 a.m.
NEDg	Description generation	`batch_6a39e7fe56d88190ab437b0517616a9e`	completed	June 23, 2026, 1:57 a.m.
NED2	Entity disambiguation (via description)	`batch_6a39ed0fdd188190b4907f10ddafa856`	completed	June 23, 2026, 2:18 a.m.
PD	Predicate disambiguation	`batch_69feea5f27748190b223ee4e3ba5a678`	completed	May 9, 2026, 8:03 a.m.

Created at: May 3, 2026, 4:11 p.m.