Triple
T16102382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States pavilion at Expo 67 |
E390652
|
entity |
| Predicate | afterFire |
P48782
|
FINISHED |
| Object | steel structure left exposed |
—
|
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: steel structure left exposed | Statement: [United States pavilion at Expo 67, afterFire, steel structure left exposed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: afterFire Context triple: [United States pavilion at Expo 67, afterFire, steel structure left exposed]
-
A.
afterRelease
Indicates that one event, action, or state occurs subsequent to the release of another entity or condition.
-
B.
after
Indicates that one event, state, or action occurs later in time than another, following it in temporal order.
-
C.
afterAD
Indicates that one event, action, or state occurs later in time than another, serving as its temporal successor.
-
D.
aftermathOf
chosen
Indicates that one event, state, or condition occurs as a consequence or result following another event.
-
E.
firedBy
Indicates that one entity has dismissed or terminated another entity from a position, role, or employment.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1ff6976ec8190b499e99b196b0285 |
completed | April 17, 2026, 9:37 a.m. |
| PD | Predicate disambiguation | batch_69e182804208819087f35307cd6e4103 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5 a.m.