Triple
T20798973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mnong people |
E511987
|
entity |
| Predicate | livelihoodChallenge |
P71878
|
FINISHED |
| Object | deforestation |
—
|
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: deforestation | Statement: [Mnong people, livelihoodChallenge, deforestation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: livelihoodChallenge Context triple: [Mnong people, livelihoodChallenge, deforestation]
-
A.
livelihood
Indicates that one entity serves as the primary means of support, income, or subsistence for another entity.
-
B.
livelihoodChange
Indicates a change in a person’s or group’s means of making a living, such as improvements, declines, or shifts in income-generating activities.
-
C.
cultivationChallenge
Indicates a situation where the process of cultivating or growing something faces difficulty, obstacles, or increased effort.
-
D.
planningChallenge
Indicates a situation where creating, organizing, or coordinating a plan is difficult or problematic for the involved entities.
-
E.
currentChallenges
chosen
Indicates the difficulties or obstacles an entity is presently facing or dealing with.
- 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_69e0b4cc69f481908e98751e697b9df4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2aef2e08190a779ed1d516ecba7 |
completed | April 21, 2026, 12:19 a.m. |
| PD | Predicate disambiguation | batch_69e5c0575b1c81908d010223fcd1213e |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:39 p.m.