Triple
T5786090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hoa Hakananaiʻa |
E128271
|
entity |
| Predicate | orientationInMuseum |
P65832
|
FINISHED |
| Object | facing visitors with back petroglyphs visible |
—
|
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: facing visitors with back petroglyphs visible | Statement: [Hoa Hakananaiʻa, orientationInMuseum, facing visitors with back petroglyphs visible]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orientationInMuseum Context triple: [Hoa Hakananaiʻa, orientationInMuseum, facing visitors with back petroglyphs visible]
-
A.
museumDisplayType
Indicates the manner or format in which items are presented or exhibited within a museum setting.
-
B.
museumAt
Indicates that an entity (such as an exhibit, artifact, or event) is located at or associated with a particular museum.
-
C.
museumSection
Indicates that one entity is a section, area, or subdivision within a museum associated with the other entity.
-
D.
museumFocus
Indicates that a museum is primarily dedicated to or specializes in a particular subject, theme, or type of collection.
-
E.
museumHolds
Indicates that a museum possesses, preserves, or has custody of a particular item or collection within its holdings.
- 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_69c0084450048190bc647b649a05136b |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02a1c29d48190af36cc855bb491dd |
completed | March 22, 2026, 5:42 p.m. |
| PD | Predicate disambiguation | batch_69c021d2cd608190b98a7e3aa7001d27 |
completed | March 22, 2026, 5:07 p.m. |
| PDg | Predicate description generation | batch_69c024861bc88190a17782c1982fbb3e |
completed | March 22, 2026, 5:19 p.m. |
Created at: March 22, 2026, 3:51 p.m.