Triple
T38306314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chachapoyan temple |
E1032353
|
entity |
| Predicate | guardedByCharacter |
P168690
|
FINISHED |
| Object | Satipo |
—
|
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: Satipo | Statement: [Chachapoyan temple, guardedByCharacter, Satipo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardedByCharacter Context triple: [Chachapoyan temple, guardedByCharacter, Satipo]
-
A.
guardedByInFiction
Indicates that one fictional entity is protected or watched over by another within a narrative context.
-
B.
guardedIn
chosen
Indicates that one entity is protected or kept under watch within the bounds or premises of another entity.
-
C.
guardedAs
Indicates that one entity is protected, watched over, or kept secure in the role or capacity specified by another entity.
-
D.
allyOfCharacter
Indicates that one character maintains an alliance or supportive partnership with another character.
-
E.
heldByCharacterType
Indicates that something (such as an item, role, or status) is possessed or carried by a character of a specified 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_69f76e0f2084819091299d021625c3fe |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fcdf2394748190b35cead3e208447d |
completed | May 7, 2026, 6:51 p.m. |
| PD | Predicate disambiguation | batch_69fcdbe344ec8190a0471911952f4b82 |
completed | May 7, 2026, 6:37 p.m. |
Created at: May 3, 2026, 4:30 p.m.