Triple

T36733884

Position	Surface form	Disambiguated ID	Type / Status
Subject	Fort Ternan	`E907412`	entity
Predicate	hasNearbyMuseumOrSite	`P179009`	FINISHED
Object	Fort Ternan prehistoric site Fort Ternan prehistoric site is an important archaeological location in Kenya known for yielding significant Miocene fossil remains, including early ape fossils that have contributed to the study of human evolution.	`E2197329`	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: Fort Ternan prehistoric site | Statement: [Fort Ternan, hasNearbyMuseumOrSite, Fort Ternan prehistoric site]

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: Fort Ternan prehistoric site
Triple: [Fort Ternan, hasNearbyMuseumOrSite, Fort Ternan prehistoric site]

Generated description

Fort Ternan prehistoric site is an important archaeological location in Kenya known for yielding significant Miocene fossil remains, including early ape fossils that have contributed to the study of human evolution.

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

Target predicate: hasNearbyMuseumOrSite
Context triple: [Fort Ternan, hasNearbyMuseumOrSite, Fort Ternan prehistoric site]

A. nearCulturalInstitution
Indicates that one entity is located close to, or in the immediate vicinity of, a cultural institution such as a museum, theater, gallery, or similar venue.
B. hasNearbyPilgrimageSite
Indicates that one entity is located close to a place used as a pilgrimage site for religious or spiritual journeys.
C. nearbyHeritageDestinations chosen
Indicates that one or more heritage destinations are located close to a given reference point or entity in geographic space.
D. hasClubMuseumNearby
Indicates that a club has a museum located in close physical proximity to it.
E. hasNearbyArchaeologicalSite
Indicates that an entity is located close to or in the vicinity of an archaeological site.
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_69f76e75aa6881909b844d00a3888ee5`	completed	May 3, 2026, 3:49 p.m.
NER	Named-entity recognition	`batch_6a006be462288190ae18e1567e2ad29f`	completed	May 10, 2026, 11:28 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a3c172b8e8c8190a8804c4ed046da1b`	completed	June 24, 2026, 5:43 p.m.
NEDg	Description generation	`batch_6a3c19646eac819096e841516ac186d9`	completed	June 24, 2026, 5:52 p.m.
NED2	Entity disambiguation (via description)	`batch_6a3c58b6b1d881909f0d5fdf14de5777`	completed	June 24, 2026, 10:22 p.m.
PD	Predicate disambiguation	`batch_6a0069e7a424819098d38458c3823605`	completed	May 10, 2026, 11:20 a.m.

Created at: May 3, 2026, 4:12 p.m.