Triple
T34672047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Awetí language |
E890400
|
entity |
| Predicate | hasFieldworkIn |
P124153
|
FINISHED |
| Object | Upper Xingu Indigenous communities |
—
|
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: Upper Xingu Indigenous communities | Statement: [Awetí language, hasFieldworkIn, Upper Xingu Indigenous communities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFieldworkIn Context triple: [Awetí language, hasFieldworkIn, Upper Xingu Indigenous communities]
-
A.
hasConductedFieldworkOn
chosen
Indicates that an agent has performed research or investigative fieldwork focused on a particular subject, location, or population.
-
B.
hasWorkField
Indicates that an entity is associated with or operates within a particular field or area of work.
-
C.
fieldworkCountry
Indicates the country in which the fieldwork or on-site research activity takes place.
-
D.
hasWorkedIn
Indicates that a person has been employed or has performed work within a particular organization, location, or domain for some period of time.
-
E.
hasWorkExhibited
Indicates that a person or creator has had their work displayed or presented in an exhibition or public showing.
- 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_69f349d9c59481908b36baa0be093aea |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff90b673248190b4dda9e005642d17 |
completed | May 9, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69ff8d5bee1081909274052945e98a6f |
completed | May 9, 2026, 7:39 p.m. |
Created at: May 1, 2026, 2:05 a.m.