Triple
T31932716
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karajarri people |
E815296
|
entity |
| Predicate | haveStrongConnectionTo |
P96771
|
FINISHED |
| Object | waterholes |
—
|
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: waterholes | Statement: [Karajarri people, haveStrongConnectionTo, waterholes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haveStrongConnectionTo Context triple: [Karajarri people, haveStrongConnectionTo, waterholes]
-
A.
hasStrongTiesTo
chosen
Indicates a close, influential, and enduring relationship or connection exists between the referenced entities.
-
B.
hasConnectionPotential
Indicates that there exists a possibility or capacity for a meaningful connection or relationship to form between the entities.
-
C.
connectsTo
Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
-
D.
hasNotableConnectionTo
Indicates a significant or noteworthy relationship, association, or link exists between two entities.
-
E.
hasTeleconnectionsWith
Indicates a relationship where changes or variations in one system, region, or variable are statistically linked to corresponding changes in another, often distant, system, region, or variable.
- 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_69f348f3035c81908558e2339955abb3 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b2311c7481909fdfa0067f3b5082 |
completed | May 3, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69f6aca7081881909e96a8b05ec086bb |
completed | May 3, 2026, 2:02 a.m. |
Created at: May 1, 2026, 12:04 a.m.