Triple
T27800042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geku (Outer Shrine) |
E702214
|
entity |
| Predicate | otherMainSanctuary |
P86570
|
FINISHED |
| Object | Naikū (Inner Shrine) |
—
|
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: Naikū (Inner Shrine) | Statement: [Geku (Outer Shrine), otherMainSanctuary, Naikū (Inner Shrine)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: otherMainSanctuary Context triple: [Geku (Outer Shrine), otherMainSanctuary, Naikū (Inner Shrine)]
-
A.
hasMajorSanctuary
Indicates that an entity possesses or is associated with a primary or principal sanctuary location.
-
B.
isLinkedToSanctuary
Indicates that an entity has a connection or association with a sanctuary, such as being related, directed, or assigned to it.
-
C.
governedSanctuary
Indicates that an entity holds governing authority or administrative control over a sanctuary.
-
D.
hadSanctuaryOf
Indicates that an entity possessed or hosted a sanctuary dedicated to another entity.
-
E.
otherRelatedSanctums
chosen
Indicates that there exist additional sanctums that are related or connected to a given sanctum in some relevant way.
- 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_69ef8408e0588190977cffa32dc33a29 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f68805b4848190b75da14996d52a38 |
completed | May 2, 2026, 11:25 p.m. |
| PD | Predicate disambiguation | batch_69f68609c0b08190a8e1238a4d97c270 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 27, 2026, 5:33 p.m.