Triple
T798973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Italy |
E17084
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object |
Isernia
Isernia is a historic town and provincial capital in the Molise region of southern-central Italy, known for its ancient Samnite and Roman roots.
|
E210581
|
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: Isernia | Statement: [Central Italy, containsCity, Isernia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isernia Context triple: [Central Italy, containsCity, Isernia]
-
A.
Teramo
Teramo is a historic city in the Abruzzo region of central Italy, known for its Roman archaeological remains and medieval architecture.
-
B.
Civitanova Marche
Civitanova Marche is a coastal town and popular seaside resort on the Adriatic Sea in the Marche region of central Italy.
-
C.
Campobasso
Campobasso is a historic city in southern-central Italy that serves as the capital of the Molise region, known for its medieval castle and traditional craftsmanship.
-
D.
Terni
Terni is an industrial city in the Umbria region of central Italy, known for its steel production and historic Roman and medieval heritage.
-
E.
Chieti
Chieti is an ancient city in the Abruzzo region of central Italy, known for its Roman archaeological sites and medieval architecture.
- 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: Isernia Triple: [Central Italy, containsCity, Isernia]
Generated description
Isernia is a historic town and provincial capital in the Molise region of southern-central Italy, known for its ancient Samnite and Roman roots.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Isernia Target entity description: Isernia is a historic town and provincial capital in the Molise region of southern-central Italy, known for its ancient Samnite and Roman roots.
-
A.
Teramo
Teramo is a historic city in the Abruzzo region of central Italy, known for its Roman archaeological remains and medieval architecture.
-
B.
Civitanova Marche
Civitanova Marche is a coastal town and popular seaside resort on the Adriatic Sea in the Marche region of central Italy.
-
C.
Campobasso
Campobasso is a historic city in southern-central Italy that serves as the capital of the Molise region, known for its medieval castle and traditional craftsmanship.
-
D.
Terni
Terni is an industrial city in the Umbria region of central Italy, known for its steel production and historic Roman and medieval heritage.
-
E.
Chieti
Chieti is an ancient city in the Abruzzo region of central Italy, known for its Roman archaeological sites and medieval architecture.
- 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_69a49378b9c48190adbf5f62e5b7aca1 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a7b4d9548190aad5fdf1211cf8cd |
completed | March 1, 2026, 8:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69addf0e902881909690c8c80abfa8c0 |
completed | March 8, 2026, 8:41 p.m. |
| NEDg | Description generation | batch_69addfb3860481908ff4eebfa3d06fa7 |
completed | March 8, 2026, 8:44 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ade027072481909b707bbfc47da4de |
completed | March 8, 2026, 8:46 p.m. |
Created at: March 1, 2026, 7:38 p.m.