Triple
T17681963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taranto harbor |
E440791
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Mar Grande
Mar Grande is the outer, larger basin of the port of Taranto in southern Italy, opening onto the Ionian Sea and serving as a key natural harbor area.
|
E1281887
|
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: Mar Grande | Statement: [Taranto harbor, hasPart, Mar Grande]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mar Grande Context triple: [Taranto harbor, hasPart, Mar Grande]
-
A.
Casarosa
Casarosa is an Italian surname most notably associated with Enrico Casarosa, the animator and director known for his work at Pixar.
-
B.
Gormezano
Gormezano is the original Sephardic Jewish family surname of American singer Eydie Gormé, reflecting her Spanish-Jewish heritage.
-
C.
Molinaro
Molinaro is an Italian occupational surname, historically associated with millers and derived from the same root as "Molinero."
-
D.
Baldovino
Baldovino is an Italian given name, historically used in medieval Europe and related to the name Baldwin.
-
E.
Ambrogio
Ambrogio is an Italian given name, historically borne by notable figures such as generals, artists, and saints.
- 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: Mar Grande Triple: [Taranto harbor, hasPart, Mar Grande]
Generated description
Mar Grande is the outer, larger basin of the port of Taranto in southern Italy, opening onto the Ionian Sea and serving as a key natural harbor area.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mar Grande Target entity description: Mar Grande is the outer, larger basin of the port of Taranto in southern Italy, opening onto the Ionian Sea and serving as a key natural harbor area.
-
A.
Casarosa
Casarosa is an Italian surname most notably associated with Enrico Casarosa, the animator and director known for his work at Pixar.
-
B.
Gormezano
Gormezano is the original Sephardic Jewish family surname of American singer Eydie Gormé, reflecting her Spanish-Jewish heritage.
-
C.
Molinaro
Molinaro is an Italian occupational surname, historically associated with millers and derived from the same root as "Molinero."
-
D.
Baldovino
Baldovino is an Italian given name, historically used in medieval Europe and related to the name Baldwin.
-
E.
Ambrogio
Ambrogio is an Italian given name, historically borne by notable figures such as generals, artists, and saints.
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4704514d481908aad4172fa930e6b |
completed | April 19, 2026, 6:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a02232a4d488190b43226ba2f34e7c0 |
completed | May 11, 2026, 6:42 p.m. |
| NEDg | Description generation | batch_6a022446c9d881908ffd0f48e06f5c0e |
completed | May 11, 2026, 6:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0224b3b33881909190dbb5752c758d |
completed | May 11, 2026, 6:49 p.m. |
Created at: April 10, 2026, 10:02 a.m.