Triple

T38419893
Position Surface form Disambiguated ID Type / Status
Subject Conference of Catholic Bishops of the Pacific E903199 entity
Predicate hasMember P10 FINISHED
Object Diocese of Taiohae o Tefenuaenata
The Diocese of Taiohae o Tefenuaenata is a Roman Catholic diocese serving the Marquesas Islands in French Polynesia.
E2281075 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: Diocese of Taiohae o Tefenuaenata | Statement: [Conference of Catholic Bishops of the Pacific, hasMember, Diocese of Taiohae o Tefenuaenata]
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: Diocese of Taiohae o Tefenuaenata
Triple: [Conference of Catholic Bishops of the Pacific, hasMember, Diocese of Taiohae o Tefenuaenata]
Generated description
The Diocese of Taiohae o Tefenuaenata is a Roman Catholic diocese serving the Marquesas Islands in French Polynesia.

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_69f76e67e4fc8190a7d08dfe9a8af998 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69fccd8864908190a7510c8ff0c3df6c completed May 7, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a4205ac04708190a077c4e6076450c8 completed June 29, 2026, 5:42 a.m.
NEDg Description generation batch_6a42061f71dc8190aeca79f1cf65aff2 completed June 29, 2026, 5:43 a.m.
NED2 Entity disambiguation (via description) batch_6a42067af3e08190856a4cd5a991c9b0 completed June 29, 2026, 5:45 a.m.
Created at: May 3, 2026, 4:31 p.m.