Triple
T25902827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marapu culture |
E652664
|
entity |
| Predicate | hasFuneraryFeature |
P68077
|
FINISHED |
| Object | buffalo sacrifice at burials |
—
|
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: buffalo sacrifice at burials | Statement: [Marapu culture, hasFuneraryFeature, buffalo sacrifice at burials]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFuneraryFeature Context triple: [Marapu culture, hasFuneraryFeature, buffalo sacrifice at burials]
-
A.
burialSiteFeature
chosen
Indicates a specific physical characteristic or element associated with a burial site, such as structures, markers, or other notable features present at the place of interment.
-
B.
hasBurialMonumentType
Indicates that an entity is associated with a burial whose monument is of a specified type.
-
C.
hasBurialsFrom
Indicates that a location or site contains burials originating from a specified time period, culture, or source.
-
D.
hasBurialsOf
Indicates that a location or site contains or includes the burial places of certain individuals or groups.
-
E.
hasBurialVault
Indicates that an entity possesses or is associated with a specific burial vault used for interment or storage of remains.
- 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_69e7ab3d3f8481909bc53ed64c06af33 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f603bbcc5c8190a4c63ef469e78276 |
completed | May 2, 2026, 2:01 p.m. |
| PD | Predicate disambiguation | batch_69f5afec3e94819080d9ba86cf8c866e |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 22, 2026, 8:26 a.m.