Triple
T31897853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghanima Atreides |
E814335
|
entity |
| Predicate | relationshipWithLetoII |
P207542
|
FINISHED |
| Object | deep psychic bond |
—
|
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: deep psychic bond | Statement: [Ghanima Atreides, relationshipWithLetoII, deep psychic bond]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipWithLetoII Context triple: [Ghanima Atreides, relationshipWithLetoII, deep psychic bond]
-
A.
relationshipTypeWithKaidanAlenko
Indicates the specific nature or category of the relationship an entity has with Kaidan Alenko.
-
B.
relationshipToElijahBaley
Indicates the nature or type of relationship an entity has with Elijah Baley.
-
C.
relationshipToJabba
Indicates the specific personal or social connection an entity has to Jabba, such as familial, hierarchical, or associative ties.
-
D.
relationshipToMarkWatney
Indicates the specific type of personal or social relationship an entity has with Mark Watney.
-
E.
IrulanCorrinoAlso
Indicates that something or someone is additionally associated with or identified as Irulan Corrino, in conjunction with another role or attribute.
- 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_69f348f04d7881909537fc9e7cbc670e |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e7aa0c8190bdc9ee4d54fc821b |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c7ee0388190a29faeb5cdb0950a |
completed | May 12, 2026, 7:16 p.m. |
Created at: April 30, 2026, 11:59 p.m.