Triple
T2711180
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freedom Park |
E59863
|
entity |
| Predicate | containsNamesOf |
P35337
|
FINISHED |
| Object | victims of conflicts in South African history |
—
|
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: victims of conflicts in South African history | Statement: [Freedom Park, containsNamesOf, victims of conflicts in South African history]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsNamesOf Context triple: [Freedom Park, containsNamesOf, victims of conflicts in South African history]
-
A.
fullNameIncludes
Indicates that one entity’s full name contains another specified string or name component as a substring.
-
B.
includesCommonName
Indicates that one entity contains or specifies a commonly used (non-scientific) name for another entity.
-
C.
namesAs
Indicates that one entity assigns or uses a particular name or label to refer to another entity.
-
D.
numberOfNames
Indicates the count of distinct names associated with a given entity.
-
E.
namedIn
chosen
Indicates that one entity is explicitly mentioned or referenced by name within another entity (such as a document, statement, or record).
- 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_69ab4ac92a088190bc74bca14038e3de |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda78c4f08190bb1217f08198c4cc |
completed | March 7, 2026, 7:57 a.m. |
| PD | Predicate disambiguation | batch_69abd8224c688190bb4a362360b03007 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.