Triple
T15270944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ayacucho |
E365017
|
entity |
| Predicate | exploitationMethod |
P5659
|
FINISHED |
| Object | heavy oil development techniques |
—
|
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: heavy oil development techniques | Statement: [Ayacucho, exploitationMethod, heavy oil development techniques]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exploitationMethod Context triple: [Ayacucho, exploitationMethod, heavy oil development techniques]
-
A.
exploits
Indicates that one entity unfairly or selfishly uses another entity or resource for its own advantage or benefit.
-
B.
earlyExploitationBy
Indicates that one entity takes unfair advantage of another at an early stage of their interaction, development, or process.
-
C.
exploitationBegan
Indicates the point in time when the exploitation or use of a resource, person, or system was initiated.
-
D.
эксплуатируется
Indicates that one entity is being used or operated by another, often in a way that takes advantage of its resources, capabilities, or labor.
-
E.
attackToolExample
chosen
Indicates that a specific tool or method is used as an example of how an attack is or can be carried out.
- 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_69d85a0f08408190b3c3259ae35d79d2 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0094eac848190a1740ae1aa6b28e0 |
completed | April 15, 2026, 9:55 p.m. |
| PD | Predicate disambiguation | batch_69deca90739081909bd1b797cdb8af2b |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:14 a.m.