Triple
T2917604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keelung River |
E78642
|
entity |
| Predicate | wasStraightenedIn |
P43894
|
FINISHED |
| Object | late 20th century |
—
|
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: late 20th century | Statement: [Keelung River, wasStraightenedIn, late 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasStraightenedIn Context triple: [Keelung River, wasStraightenedIn, late 20th century]
-
A.
stricken
Indicates that an entity has been severely affected, harmed, or afflicted by something (such as illness, disaster, or misfortune).
-
B.
hasStraightLines
Indicates that the related entity possesses or is characterized by straight, non-curved lines.
-
C.
strickenOn
Indicates that an item, statement, or provision has been formally removed, invalidated, or marked out as no longer in effect at a particular time or by a particular action.
-
D.
originallyHad
Indicates that an entity previously possessed, contained, or was associated with something before a change, loss, or transformation occurred.
-
E.
wereInternedBy
Indicates that an entity was forcibly confined, detained, or held in an internment facility by another entity (typically an authority or government).
- F. None of above. chosen
Provenance (4 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_69ad8b0c2ad081909ff87050ae542bb9 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad97fd89d88190bc7db4b39058ae3a |
completed | March 8, 2026, 3:38 p.m. |
| PD | Predicate disambiguation | batch_69ad9603ddd88190b8bf91bc7517cc21 |
completed | March 8, 2026, 3:30 p.m. |
| PDg | Predicate description generation | batch_69ad97f520208190a4dc43372004555f |
completed | March 8, 2026, 3:38 p.m. |
Created at: March 8, 2026, 2:54 p.m.