Triple
T34758047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broad Street Prison |
E1001981
|
entity |
| Predicate | hasMemorialAt |
P501
|
FINISHED |
| Object | Freedom Park Lagos |
—
|
NE NERFINISHED |
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: Freedom Park Lagos | Statement: [Broad Street Prison, hasMemorialAt, Freedom Park Lagos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMemorialAt Context triple: [Broad Street Prison, hasMemorialAt, Freedom Park Lagos]
-
A.
hasMemorial
chosen
Indicates that a memorial exists in honor of, or dedicated to, a particular entity.
-
B.
hasMemorialStatus
Indicates that a subject has been assigned a particular memorial-related status or designation.
-
C.
hasNearbyMemorials
Indicates that one or more memorials are located in close physical proximity to the referenced entity.
-
D.
hasMemorialContext
Indicates that something is related to, associated with, or situated within the context of a memorial or commemorative setting.
-
E.
hasMemorialWall
Indicates that a place or entity includes or is associated with a wall dedicated to commemorating people, events, or memories.
- 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_69f76db0fb30819096709d43f9a1f45f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69ff1f3f94fc819095955299f50ab4ce |
completed | May 9, 2026, 11:49 a.m. |
| PD | Predicate disambiguation | batch_69ff1ea47748819082f63d9b9d9c3e65 |
completed | May 9, 2026, 11:46 a.m. |
Created at: May 3, 2026, 3:59 p.m.