Triple
T24376633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mungo Lady |
E614492
|
entity |
| Predicate | burialPracticeDetail |
P121622
|
FINISHED |
| Object | body cremated, bones crushed and burned again |
—
|
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: body cremated, bones crushed and burned again | Statement: [Mungo Lady, burialPracticeDetail, body cremated, bones crushed and burned again]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: burialPracticeDetail Context triple: [Mungo Lady, burialPracticeDetail, body cremated, bones crushed and burned again]
-
A.
burialPractice
Indicates the customary methods, rituals, or procedures a group uses to bury or inter their dead.
-
B.
burialDetail
chosen
Indicates details about how, where, and under what circumstances an entity is buried.
-
C.
burialCulture
Indicates the cultural practices, norms, or traditions associated with how a person or remains are buried.
-
D.
burialContext
Indicates the circumstances or setting in which a burial takes place, such as associated practices, location, or cultural conditions surrounding the interment.
-
E.
burialPolicy
Indicates the rules or arrangements governing how and under what conditions a person’s body is to be buried.
- 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_69e2d7e1e010819098b95eb3f905943d |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f293d7fb188190bfab5e7ff83fa884 |
completed | April 29, 2026, 11:27 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:02 a.m.