Triple
T9098473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Alda |
E218088
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
D’Abruzzo
D’Abruzzo is an Italian surname associated with actor Robert Alda, reflecting his family’s Abruzzese heritage.
|
E787710
|
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: D’Abruzzo | Statement: [Robert Alda, familyName, D’Abruzzo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: D’Abruzzo Context triple: [Robert Alda, familyName, D’Abruzzo]
-
A.
Abruzzo
Abruzzo is a central Italian region known for its rugged Apennine mountains, national parks, and Adriatic Sea coastline.
-
B.
Molise
Molise is a small, predominantly rural region in southern Italy known for its mountainous landscapes, traditional agriculture, and relatively low population density.
-
C.
Umbria
Umbria is a central Italian region known for its historic hill towns, medieval architecture, and rich cultural heritage.
-
D.
La Marche
La Marche is a historic province in central France known for its rural landscapes and role as a frontier region between major medieval territories.
-
E.
Maremma region
The Maremma region is a coastal area of southwestern Tuscany and northern Lazio in Italy, known for its wild landscapes, medieval hill towns, and traditional agriculture.
- 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: D’Abruzzo Triple: [Robert Alda, familyName, D’Abruzzo]
Generated description
D’Abruzzo is an Italian surname associated with actor Robert Alda, reflecting his family’s Abruzzese heritage.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: D’Abruzzo Target entity description: D’Abruzzo is an Italian surname associated with actor Robert Alda, reflecting his family’s Abruzzese heritage.
-
A.
Abruzzo
Abruzzo is a central Italian region known for its rugged Apennine mountains, national parks, and Adriatic Sea coastline.
-
B.
Molise
Molise is a small, predominantly rural region in southern Italy known for its mountainous landscapes, traditional agriculture, and relatively low population density.
-
C.
Umbria
Umbria is a central Italian region known for its historic hill towns, medieval architecture, and rich cultural heritage.
-
D.
La Marche
La Marche is a historic province in central France known for its rural landscapes and role as a frontier region between major medieval territories.
-
E.
Maremma region
The Maremma region is a coastal area of southwestern Tuscany and northern Lazio in Italy, known for its wild landscapes, medieval hill towns, and traditional agriculture.
- 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_69ca83d9844081908e561e367fda6d45 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc970f340881909f5551219f151acf |
completed | April 1, 2026, 3:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d09b66432081908f557fba2cbf2f6d |
completed | April 4, 2026, 5:02 a.m. |
| NEDg | Description generation | batch_69d09cc5cdd481908903ae0e49c1085d |
completed | April 4, 2026, 5:08 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d09d7364b48190ad3dd55711bd2534 |
completed | April 4, 2026, 5:11 a.m. |
Created at: March 30, 2026, 7:15 p.m.