Triple
T3863890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aristaeus |
E91803
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Macris |
E395435
|
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: Macris | Statement: [Aristaeus, child, Macris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Macris Context triple: [Aristaeus, child, Macris]
-
A.
Macris
chosen
Macris is a figure in Greek mythology known primarily as the mother of the rustic god Aristaeus.
-
B.
Teodor
Teodor is a given name, commonly used in various European languages, that corresponds to the English name Theodore.
-
C.
Rudolf Fizir
Rudolf Fizir was a Croatian aircraft designer known for creating numerous light aircraft and trainers in the early 20th century.
-
D.
Marcetelli
Marcetelli is a small Italian municipality in the Lazio region, known for its rural character and location within the mountainous area of central Italy.
-
E.
Danilo Bach
Danilo Bach is an American screenwriter best known for originating the story that became the hit action-comedy film "Beverly Hills Cop."
- 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_69aed9645f348190a9868e7cef56ab7e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec3871d881909c6c8e6d08203801 |
completed | March 9, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b51c7d99208190baee9830cc448eee |
completed | March 14, 2026, 8:29 a.m. |
Created at: March 9, 2026, 3:19 p.m.