Triple
T220701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holy Trinity Cathedral, Port-au-Prince |
E4205
|
entity |
| Predicate | statusAfter2010 |
P10104
|
FINISHED |
| Object | largely destroyed |
—
|
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: largely destroyed | Statement: [Holy Trinity Cathedral, Port-au-Prince, statusAfter2010, largely destroyed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statusAfter2010 Context triple: [Holy Trinity Cathedral, Port-au-Prince, statusAfter2010, largely destroyed]
-
A.
declineBeganInDecade
Indicates that the period of decline for an entity or phenomenon started during the specified decade.
-
B.
emergedInDecade
Indicates that something first appeared, originated, or came into prominence during a specified decade.
-
C.
activeInDecade
Indicates that an entity was active or engaged in its primary activities during a specified decade.
-
D.
statusAfter1956
Indicates the status or condition of an entity as it existed at any time after the year 1956.
-
E.
tookPlaceAfter
Indicates that one event or occurrence happened later in time than another event or occurrence.
- 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_69a2573508588190b522c2476d91acfe |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25efd0df48190b8fef4c422a1265f |
completed | Feb. 28, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69a25b54d790819093b35bd1a6f00f92 |
completed | Feb. 28, 2026, 3:04 a.m. |
| PDg | Predicate description generation | batch_69a25efc13308190900a86ca0367c9b3 |
completed | Feb. 28, 2026, 3:20 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.