Triple
T4199874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umbrians |
E86039
|
entity |
| Predicate | majorSite |
P2462
|
FINISHED |
| Object |
Spoletium
Spoletium was an important ancient Umbrian city in central Italy, later known as the Roman colony of Spoletium (modern Spoleto).
|
E419010
|
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: Spoletium | Statement: [Umbrians, majorSite, Spoletium]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Spoletium Context triple: [Umbrians, majorSite, Spoletium]
-
A.
Asculum
Asculum was an important ancient city in central Italy, historically serving as the chief urban center of the Piceni people.
-
B.
Maenza
Maenza is a small historic town in the Lazio region of central Italy, known for its medieval architecture and hilltop setting.
-
C.
Clusium
Clusium was an important ancient Etruscan city, known for its strategic location in central Italy and its significant role in early Roman history.
-
D.
Arpinum
Arpinum is an ancient Italian town in Latium best known as the birthplace of the Roman statesman and orator Cicero.
-
E.
Sogliano al Rubicone
Sogliano al Rubicone is a small Italian town in the Emilia-Romagna region, known for its historic center and traditional production of formaggio di fossa (pit-aged cheese).
- 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: Spoletium Triple: [Umbrians, majorSite, Spoletium]
Generated description
Spoletium was an important ancient Umbrian city in central Italy, later known as the Roman colony of Spoletium (modern Spoleto).
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Spoletium Target entity description: Spoletium was an important ancient Umbrian city in central Italy, later known as the Roman colony of Spoletium (modern Spoleto).
-
A.
Asculum
Asculum was an important ancient city in central Italy, historically serving as the chief urban center of the Piceni people.
-
B.
Maenza
Maenza is a small historic town in the Lazio region of central Italy, known for its medieval architecture and hilltop setting.
-
C.
Clusium
Clusium was an important ancient Etruscan city, known for its strategic location in central Italy and its significant role in early Roman history.
-
D.
Arpinum
Arpinum is an ancient Italian town in Latium best known as the birthplace of the Roman statesman and orator Cicero.
-
E.
Sogliano al Rubicone
Sogliano al Rubicone is a small Italian town in the Emilia-Romagna region, known for its historic center and traditional production of formaggio di fossa (pit-aged cheese).
- 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_69aed93b89f48190a31f6d57c760e42f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0363bbb8819093f396afe91972e2 |
completed | March 9, 2026, 5:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b58a14eda88190aaca14644c3e041a |
completed | March 14, 2026, 4:17 p.m. |
| NEDg | Description generation | batch_69b58ae74ef481908a21ab5f649750e3 |
completed | March 14, 2026, 4:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b58b7aad248190ac4f25fb424e9217 |
completed | March 14, 2026, 4:23 p.m. |
Created at: March 9, 2026, 3:49 p.m.