Triple

T28183736

Position	Surface form	Disambiguated ID	Type / Status
Subject	Færder Lighthouse	`E716110`	entity
Predicate	previousLightLocation	`P64595`	FINISHED
Object	Store Færder Store Færder is an island in Norway’s outer Oslofjord that historically served as the site of earlier lighthouse installations guiding maritime traffic along the coast.	`E1805697`	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: Store Færder | Statement: [Færder Lighthouse, previousLightLocation, Store Færder]

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: Store Færder
Triple: [Færder Lighthouse, previousLightLocation, Store Færder]

Generated description

Store Færder is an island in Norway’s outer Oslofjord that historically served as the site of earlier lighthouse installations guiding maritime traffic along the coast.

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

Target predicate: previousLightLocation
Context triple: [Færder Lighthouse, previousLightLocation, Store Færder]

A. lightOrganLocation
Indicates the anatomical location or placement of a light-producing organ within or on an organism.
B. laterLightSource
Indicates that one light source occurs or is activated after another in time.
C. previousLightStations chosen
Indicates that one light station existed earlier in time or sequence than another related light station.
D. torchLightingLocation
Indicates the location where a torch is or should be lit in relation to another entity or environment.
E. previousLocationName
Indicates that one entity specifies the name of a location where another entity was situated or occurred before its current location.
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_69efd6b4fc5c81909dd88f01a8c2b35d`	completed	April 27, 2026, 9:35 p.m.
NER	Named-entity recognition	`batch_69fcf1b3d9a08190850b388308656266`	completed	May 7, 2026, 8:10 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a15d7c90468819095f6f789ea6b3bc0`	completed	May 26, 2026, 5:26 p.m.
NEDg	Description generation	`batch_6a15dbaf1224819090a0ec3d323a8601`	completed	May 26, 2026, 5:43 p.m.
NED2	Entity disambiguation (via description)	`batch_6a15dc178a708190927987ae171664eb`	completed	May 26, 2026, 5:44 p.m.
PD	Predicate disambiguation	`batch_69fcf0226d8c8190b23dceafb1794995`	completed	May 7, 2026, 8:03 p.m.

Created at: April 27, 2026, 10:21 p.m.