Triple
T23127764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phorcides |
E577079
|
entity |
| Predicate | siblingOf |
P363
|
FINISHED |
| Object | Gorgons |
—
|
NE NERFINISHED |
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: Gorgons | Statement: [Phorcides, siblingOf, Gorgons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gorgons Context triple: [Phorcides, siblingOf, Gorgons]
-
A.
Gorgons
chosen
The Gorgons are monstrous sisters from Greek mythology, most famously including Medusa, whose petrifying gaze could turn onlookers to stone.
-
B.
Gorgon
Gorgon is a monstrous figure from Greek mythology, most famously represented by Medusa, whose gaze could turn onlookers to stone.
-
C.
Gorgon
Gorgon is a powerful Inhuman warrior known for his superhuman strength and seismic, shockwave-generating hooves, often serving as a key member of the Inhuman Royal Family.
-
D.
Graeae
The Graeae are three ancient Greek mythological sisters who share a single eye and tooth among them and are consulted by Perseus on his quest to defeat Medusa.
-
E.
Medusa
Medusa is a famous monster from Greek mythology, typically depicted as a winged woman with snakes for hair whose gaze turns onlookers to stone.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245f7b0e481909c473ff4e6a54e2c |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e55aa38819092816ffc52e20dbe |
completed | April 29, 2026, 4:51 a.m. |
Created at: April 17, 2026, 3:59 p.m.