Triple
T22989223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kangson enrichment site (alleged) |
E572000
|
entity |
| Predicate | publiclyDiscussedSince |
P112060
|
FINISHED |
| Object | around 2018 |
—
|
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: around 2018 | Statement: [Kangson enrichment site (alleged), publiclyDiscussedSince, around 2018]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publiclyDiscussedSince Context triple: [Kangson enrichment site (alleged), publiclyDiscussedSince, around 2018]
-
A.
coveredSince
Indicates that one entity has been under the protection, applicability, or effect of another entity continuously starting from a specified point in time.
-
B.
knownSince
Indicates the point in time from which one entity has been aware of, acquainted with, or in possession of knowledge about another entity.
-
C.
representedSince
Indicates that one entity has been acting as a representative or agent for another entity continuously from a specified starting time.
-
D.
discoveredSince
Indicates that one entity has been discovered starting from, or at some point after, a specified time or event associated with another entity.
-
E.
mentionedSince
chosen
Indicates that one entity has been mentioned or referred to continuously or at least once from a specified point in time onward.
- 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_69e245b535808190adef8a9df3c584db |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182ea55cc8190b64b722ce8c45b53 |
completed | April 29, 2026, 4:02 a.m. |
| PD | Predicate disambiguation | batch_69ef3b974e7c8190b8be11dbb4518693 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:49 p.m.