Triple
T3980615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gorgoneion |
E85746
|
entity |
| Predicate | relatedConcept |
P37
|
FINISHED |
| Object | Medusa head |
E85746
|
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: Medusa head | Statement: [Gorgoneion, relatedConcept, Medusa head]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Medusa head Context triple: [Gorgoneion, relatedConcept, Medusa head]
-
A.
Gorgoneion
chosen
The Gorgoneion is an ancient apotropaic emblem depicting the severed, snake-haired head of a Gorgon, widely used in Greek art and armor to ward off evil.
-
B.
Medusa
Medusa is a famous painting by the Italian Baroque artist Caravaggio depicting the severed, snake-haired head of the Gorgon from Greek mythology at the moment of her death.
-
C.
Basilisk
The Basilisk is a gigantic, deadly serpent from the Harry Potter series whose gaze can kill and whose venom is among the most lethal magical substances.
-
D.
Moor's head
Moor's head is a heraldic emblem depicting a black African head, famously used on the flag and coat of arms of Corsica.
-
E.
Gorgons
The Gorgons are monstrous sisters from Greek mythology, most famously including Medusa, whose petrifying gaze could turn onlookers to stone.
- 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_69aed93908348190a26c8aaf4fab3e86 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef9d9d8848190aa06eaf5d281fa16 |
completed | March 9, 2026, 4:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b54021ae388190a9518ea85b760736 |
completed | March 14, 2026, 11:01 a.m. |
Created at: March 9, 2026, 3:33 p.m.