Triple
T12665997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antonio I Acciaioli |
E302554
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Acciaioli |
E993948
|
NE FINISHED |
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: Acciaioli | Statement: [Antonio I Acciaioli, familyName, Acciaioli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Acciaioli Context triple: [Antonio I Acciaioli, familyName, Acciaioli]
-
A.
Acciaioli
chosen
Acciaioli is an Italian noble family historically prominent in banking and politics, particularly in medieval Florence and Greece.
-
B.
Ferno
Ferno is a small municipality in the Lombardy region of northern Italy, situated in the province of Varese.
-
C.
Ferro
Ferro is an alternative name for El Hierro, the smallest and westernmost of Spain’s Canary Islands in the Atlantic Ocean.
-
D.
The Iron
The Iron is the nickname of Scunthorpe United F.C., an English professional football club traditionally associated with the town’s steel industry.
-
E.
The Iron
The Iron is the English title of Surah Al-Hadid, the 57th chapter of the Qur’an, which emphasizes faith, charity, and the transient nature of worldly life.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d7bded71a88190bb76e2413af9ea66 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9617e030881908444743b8a7e0d75 |
completed | April 10, 2026, 8:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6719de0908190bbc9a98e67e5b6eb |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:19 p.m.