Triple
T22667476
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sfax Governorate |
E559828
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Skhira |
—
|
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: Skhira | Statement: [Sfax Governorate, contains, Skhira]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Skhira Context triple: [Sfax Governorate, contains, Skhira]
-
A.
Skhira
chosen
Skhira is a coastal town in southeastern Tunisia known for its port facilities and role in the regional oil and chemical industries.
-
B.
Zefta
Zefta is a village located in southern Lebanon within the Nabatieh Governorate.
-
C.
Marassi
Marassi is a residential district of Genoa, Italy, best known for hosting the historic Stadio Luigi Ferraris football stadium.
-
D.
Kalloni
Kalloni is a town on the Greek island of Lesbos, known for its large bay, salt pans, and rich birdlife.
-
E.
Taris
Taris is a heavily urbanized, stratified ecumenopolis world in the Star Wars universe, best known for its prominent role in the Old Republic era stories and games.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454a158c819093b8e35f5045efb6 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1781ceca08190ba1309570e81c5af |
completed | April 29, 2026, 3:16 a.m. |
Created at: April 17, 2026, 3:09 p.m.