Triple
T12165601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ahu Akivi |
E289824
|
entity |
| Predicate | hasMoaiPosture |
P42040
|
FINISHED |
| Object | upright standing |
—
|
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: upright standing | Statement: [Ahu Akivi, hasMoaiPosture, upright standing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMoaiPosture Context triple: [Ahu Akivi, hasMoaiPosture, upright standing]
-
A.
describesPosture
chosen
Indicates that one entity specifies or characterizes the bodily position or stance (posture) of another entity.
-
B.
hasMoaiWithPukao
Indicates that something includes or features a moai statue that is specifically topped with a pukao (a stone hat or topknot).
-
C.
proceduralPosture
Indicates the current stage or status of a legal case within the judicial or administrative process at the time it is being considered or described.
-
D.
hasSeatingPose
Indicates that an entity is in a seated posture or arrangement, specifying how it is positioned while sitting.
-
E.
hasLiturgicalPosture
Indicates that an entity is associated with a specific bodily posture or position used in a liturgical or religious ritual context.
- 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_69d6ab4d6c00819095a9a7c35de83cfb |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d91621ca6c81908365732f361aef13 |
completed | April 10, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69d9150e85348190b9b47cda4a17dcd0 |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:50 p.m.