Triple

T38225861
Position Surface form Disambiguated ID Type / Status
Subject Demetae E1012142 entity
Predicate hasMajorSettlement P316 FINISHED
Object Loughor (Roman fort)
Loughor (Roman fort) is a Roman military fort and settlement site in southwest Wales that served as a strategic outpost in the territory of the ancient Demetae tribe.
E2260643 NE FINISHED

How this triple was built (2 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: Loughor (Roman fort) | Statement: [Demetae, hasMajorSettlement, Loughor (Roman fort)]
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: Loughor (Roman fort)
Triple: [Demetae, hasMajorSettlement, Loughor (Roman fort)]
Generated description
Loughor (Roman fort) is a Roman military fort and settlement site in southwest Wales that served as a strategic outpost in the territory of the ancient Demetae tribe.

Provenance (5 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_69f76dd25e0c81909f2abd0803e5e3ee completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69fcb15f93bc819090269e9e57085091 completed May 7, 2026, 3:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a4185551a988190a4ff1daa2a93369d completed June 28, 2026, 8:34 p.m.
NEDg Description generation batch_6a418656494881908409b6ed7f5bf2a5 completed June 28, 2026, 8:38 p.m.
NED2 Entity disambiguation (via description) batch_6a41870347b0819084084ebb3013c1a1 completed June 28, 2026, 8:41 p.m.
Created at: May 3, 2026, 4:30 p.m.