Triple
T17917621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abai |
E447972
|
entity |
| Predicate | oracleReputation |
P129315
|
FINISHED |
| Object | consulted by Greeks for divination |
—
|
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: consulted by Greeks for divination | Statement: [Abai, oracleReputation, consulted by Greeks for divination]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oracleReputation Context triple: [Abai, oracleReputation, consulted by Greeks for divination]
-
A.
engineeringReputation
Indicates the perceived quality, credibility, or esteem of an entity’s engineering capabilities or output as judged by others.
-
B.
scoringReputation
Indicates that one entity evaluates and assigns a reputation-related score to another entity based on its behavior or performance.
-
C.
crowdReputation
Indicates the collective opinion or perceived standing of an entity as judged by a group or general audience.
-
D.
securityReputation
Indicates the assessed trustworthiness or risk level associated with an entity’s security posture or behavior.
-
E.
liveReputation
Indicates a dynamic, continuously updated assessment of an entity’s standing, trustworthiness, or performance based on recent or real-time information.
- F. None of above. chosen
Provenance (4 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a30778fc81908b5b2e308fb158a5 |
completed | April 19, 2026, 9:40 a.m. |
| PD | Predicate disambiguation | batch_69e3d8ec2f6881909d7f54b878cbed37 |
completed | April 18, 2026, 7:18 p.m. |
| PDg | Predicate description generation | batch_69e3db77df0c819084548168c62b398c |
completed | April 18, 2026, 7:28 p.m. |
Created at: April 10, 2026, 10:20 a.m.