Triple
T15455681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maroneia |
E371763
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object |
Maron
Maron is a figure from Greek mythology, often depicted as a priest of Apollo and a son or companion of Dionysus associated with the region of Thrace.
|
E1157574
|
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: Maron | Statement: [Maroneia, namedAfter, Maron]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maron Context triple: [Maroneia, namedAfter, Maron]
-
A.
Maron
Maron is a semi-autobiographical comedy television series created by and starring comedian Marc Maron, loosely based on his life and career.
-
B.
Marino
Marino is a surname most famously associated with Dan Marino, the Hall of Fame former NFL quarterback for the Miami Dolphins.
-
C.
Marino
Marino is a historic town in Italy’s Alban Hills near Rome, known for its wine production and annual grape festival.
-
D.
Maron (TV series)
Maron is a semi-autobiographical comedy series created by and starring comedian Marc Maron, loosely based on his life and popular WTF podcast.
-
E.
Mateur
Mateur is a town in northern Tunisia known as an agricultural and transport hub situated near Lake Ichkeul.
- 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: Maron Triple: [Maroneia, namedAfter, Maron]
Generated description
Maron is a figure from Greek mythology, often depicted as a priest of Apollo and a son or companion of Dionysus associated with the region of Thrace.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Maron Target entity description: Maron is a figure from Greek mythology, often depicted as a priest of Apollo and a son or companion of Dionysus associated with the region of Thrace.
-
A.
Maron
Maron is a semi-autobiographical comedy television series created by and starring comedian Marc Maron, loosely based on his life and career.
-
B.
Marino
Marino is a historic town in Italy’s Alban Hills near Rome, known for its wine production and annual grape festival.
-
C.
Marino
Marino is a surname most famously associated with Dan Marino, the Hall of Fame former NFL quarterback for the Miami Dolphins.
-
D.
Maron (TV series)
Maron is a semi-autobiographical comedy series created by and starring comedian Marc Maron, loosely based on his life and popular WTF podcast.
-
E.
Mateur
Mateur is a town in northern Tunisia known as an agricultural and transport hub situated near Lake Ichkeul.
- 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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f146a2c8190882741af3ec15268 |
completed | April 16, 2026, 1:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff21b5e1788190bdc8182822f25fa1 |
completed | May 9, 2026, 11:59 a.m. |
| NEDg | Description generation | batch_69ff2432dce481908e469a024e31e8be |
completed | May 9, 2026, 12:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff2484bb948190985d0714b9c19ee3 |
completed | May 9, 2026, 12:11 p.m. |
Created at: April 10, 2026, 3:31 a.m.