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.