Triple
T3758472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tunis Governorate |
E82104
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
La Marsa
La Marsa is a coastal suburb of Tunis in northern Tunisia, known for its beaches, upscale residential areas, and historic seaside charm.
|
E385743
|
NE FINISHED |
How this triple was built (4 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: La Marsa | Statement: [Tunis Governorate, contains, La Marsa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: La Marsa Context triple: [Tunis Governorate, contains, La Marsa]
-
A.
Melissant
Melissant is a small village in the Dutch province of South Holland, located on the island of Goeree-Overflakkee.
-
B.
Miravalle
Miravalle is a neighborhood located within the Benito Juárez borough of Mexico City, known for its residential character and urban amenities.
-
C.
Marsa al-Brega
Marsa al-Brega is a coastal industrial town in northeastern Libya known for its major oil refinery and petrochemical facilities on the Gulf of Sidra.
-
D.
Martos
Martos is a historic town in southern Spain’s Andalusia region, known for its olive oil production and hilltop setting dominated by a medieval castle.
-
E.
Gela Sule
Gela Sule is a variant name for Nggela Sule, a locality associated with the Nggela (Florida) Islands in the Solomon Islands.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: La Marsa Triple: [Tunis Governorate, contains, La Marsa]
Generated description
La Marsa is a coastal suburb of Tunis in northern Tunisia, known for its beaches, upscale residential areas, and historic seaside charm.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: La Marsa Target entity description: La Marsa is a coastal suburb of Tunis in northern Tunisia, known for its beaches, upscale residential areas, and historic seaside charm.
-
A.
Melissant
Melissant is a small village in the Dutch province of South Holland, located on the island of Goeree-Overflakkee.
-
B.
Miravalle
Miravalle is a neighborhood located within the Benito Juárez borough of Mexico City, known for its residential character and urban amenities.
-
C.
Marsa al-Brega
Marsa al-Brega is a coastal industrial town in northeastern Libya known for its major oil refinery and petrochemical facilities on the Gulf of Sidra.
-
D.
Martos
Martos is a historic town in southern Spain’s Andalusia region, known for its olive oil production and hilltop setting dominated by a medieval castle.
-
E.
Gela Sule
Gela Sule is a variant name for Nggela Sule, a locality associated with the Nggela (Florida) Islands in the Solomon Islands.
- F. None of above. chosen
Provenance (5 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_69ad8b1db40081908b61ffa6b78afd4d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcbc20b20819095fedf803aadc53a |
completed | March 8, 2026, 7:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4e50f77fc8190b7774a7359118c9c |
completed | March 14, 2026, 4:33 a.m. |
| NEDg | Description generation | batch_69b4e5fe22f0819088effd8a0eae72e6 |
completed | March 14, 2026, 4:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4e671e02c819094cae2a3a2abb1b4 |
completed | March 14, 2026, 4:39 a.m. |
Created at: March 8, 2026, 3:35 p.m.