Triple
T13836312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Μερόπη |
E332536
|
entity |
| Predicate | χαρακτηρίζεταιΩς |
P662
|
FINISHED |
| Object | η λιγότερο λαμπρή από τις Πλειάδες |
—
|
LITERAL 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: η λιγότερο λαμπρή από τις Πλειάδες | Statement: [Μερόπη, χαρακτηρίζεταιΩς, η λιγότερο λαμπρή από τις Πλειάδες]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: χαρακτηρίζεταιΩς Context triple: [Μερόπη, χαρακτηρίζεταιΩς, η λιγότερο λαμπρή από τις Πλειάδες]
-
A.
characterizedBy
chosen
Indicates that one entity possesses a defining quality, feature, or attribute expressed by another entity.
-
B.
treatmentCharacterization
Indicates how a treatment is defined, described, or categorized in terms of its nature, properties, or distinguishing features.
-
C.
karakter
Indicates that one entity is a character (e.g., a role or persona) associated with or embodied by another entity.
-
D.
issueCharacterization
Indicates how an issue, problem, or case is categorized or described in terms of its nature, type, or defining attributes.
-
E.
relationshipCharacterizedAs
Indicates that one relationship is described, defined, or typified in terms of another specified characteristic or relational type.
- F. None of above.
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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de029b352081909605baaedc336213 |
completed | April 14, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:13 p.m.