Triple
T2692201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haitian Vodou |
E58427
|
entity |
| Predicate | metTetDefinition |
P41084
|
FINISHED |
| Object | patron lwa of an individual |
—
|
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: patron lwa of an individual | Statement: [Haitian Vodou, metTetDefinition, patron lwa of an individual]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: metTetDefinition Context triple: [Haitian Vodou, metTetDefinition, patron lwa of an individual]
-
A.
metBetween
Indicates that two or more entities had an in-person or virtual meeting or encounter with each other during a specified time or context.
-
B.
metOn
Indicates that two or more entities encountered each other at the same time and place for the first time or for a particular meeting.
-
C.
languageTerm
Indicates that one entity is a linguistic expression (word, phrase, or term) used to denote or label the other entity.
-
D.
metre
Indicates a measurement relationship where one entity’s length, distance, or size is quantified in units of metres.
-
E.
meter
Indicates a measurement relationship where one entity quantifies the length, distance, or extent of another in meters.
- 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_69ab4ac269e481909cb317d79e68b75b |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda0dd97c81909a60cf200f57c087 |
completed | March 7, 2026, 7:55 a.m. |
| PD | Predicate disambiguation | batch_69abd81ea5d88190ab5c8f8b8064b931 |
completed | March 7, 2026, 7:47 a.m. |
| PDg | Predicate description generation | batch_69abd879bb808190bd2c34de1664c816 |
completed | March 7, 2026, 7:49 a.m. |
Created at: March 6, 2026, 9:54 p.m.