Triple

T15128479
Position Surface form Disambiguated ID Type / Status
Subject Maria E361353 entity
Predicate sibling P363 FINISHED
Object Thermantia E358635 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: Thermantia | Statement: [Maria, sibling, Thermantia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thermantia
Context triple: [Maria, sibling, Thermantia]
  • A. Thermantia chosen
    Thermantia was a late Roman noblewoman who became empress as the second wife of Emperor Honorius and daughter of the powerful general Stilicho.
  • B. Therma
    Therma was an ancient settlement located on the island of Samothrace in the northern Aegean Sea.
  • C. Thera
    Thera is an ancient Greek island in the Aegean Sea, better known today as Santorini, historically significant as the homeland of colonists who founded Cyrene in North Africa.
  • D. Vromonas
    Vromonas is a small Greek island that forms part of the Echinades archipelago in the Ionian Sea.
  • E. Cadmea
    Cadmea was the ancient fortified citadel at the heart of Thebes in Boeotia, serving as its political and military stronghold.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85a06450081909c5a14ea9851a15e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e005aff2648190bda885c09421758d completed April 15, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69feb7f865c08190ab8fd15c14d0c06c completed May 9, 2026, 4:28 a.m.
Created at: April 10, 2026, 3:06 a.m.