Triple

T34894443
Position Surface form Disambiguated ID Type / Status
Subject Muhammad III as-Sadiq E1006390 entity
Predicate successorStateOutcome P189787 FINISHED
Object French protectorate of Tunisia NE NERFINISHED

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: French protectorate of Tunisia | Statement: [Muhammad III as-Sadiq, successorStateOutcome, French protectorate of Tunisia]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: successorStateOutcome
Context triple: [Muhammad III as-Sadiq, successorStateOutcome, French protectorate of Tunisia]
  • A. successorState
    Indicates that one state directly follows another as the immediate next state in a sequence or process.
  • B. successorStateFlag
    Indicates that a particular state directly follows another state in a defined sequence or process.
  • C. mainSuccessorState chosen
    Indicates the state that directly follows and replaces a given state as its primary or official successor in a sequence or process.
  • D. successorStateAffected
    Indicates that a change or event in one state directly influences or alters the conditions of its subsequent (successor) state.
  • E. successorStateBuilt
    Indicates that one state of construction or development directly follows and results from another in a building or structural process.
  • F. None of above.

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_69f76dbfe5788190ad8b64f241f470c8 completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69fff9b126b4819085a4cf8791d388d1 completed May 10, 2026, 3:21 a.m.
PD Predicate disambiguation batch_69fff8f913a881908d3b7e490d92631f completed May 10, 2026, 3:18 a.m.
Created at: May 3, 2026, 4 p.m.