Triple

T10082875
Position Surface form Disambiguated ID Type / Status
Subject Terence Morgan E213945 entity
Predicate givenName P17 FINISHED
Object Terence E18100 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: Terence | Statement: [Terence Morgan, givenName, Terence]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terence
Context triple: [Terence Morgan, givenName, Terence]
  • A. Terence chosen
    Terence is a masculine given name of Latin origin, historically associated with figures such as the Roman playwright Terence and later borne by notable individuals including the British dramatist Terence Rattigan.
  • B. Plautus
    Plautus was a Roman playwright of the Old Latin period, best known for his influential comedies that adapted and popularized Greek New Comedy for Roman audiences.
  • C. Senec
    Senec is a small town in western Slovakia known for its recreational lakes and proximity to Bratislava.
  • D. Quintus Lucilius Balbus
    Quintus Lucilius Balbus is a Stoic philosopher who appears as one of the main interlocutors in Cicero’s dialogue "De natura deorum," presenting and defending Stoic theology.
  • E. Persius
    Persius was a 1st-century Roman Stoic poet best known for his six dense, morally charged verse satires critiquing social and literary corruption.
  • 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_69ca839bf730819086900c323c9b8c95 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd04352d081908f676444cd2d2578 completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b66b256c8190861066f7c19008d2 completed April 5, 2026, 7:22 p.m.
Created at: March 30, 2026, 9 p.m.