Triple
T1027757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fox Theatre (Atlanta) |
E22178
|
entity |
| Predicate | threatenedWith |
P16824
|
FINISHED |
| Object | demolition in the 1970s |
—
|
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: demolition in the 1970s | Statement: [Fox Theatre (Atlanta), threatenedWith, demolition in the 1970s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: threatenedWith Context triple: [Fox Theatre (Atlanta), threatenedWith, demolition in the 1970s]
-
A.
threatenedBy
Indicates that one entity poses a danger or potential harm to another entity.
-
B.
threat
Indicates a relationship where one entity expresses or poses potential harm, danger, or negative consequences toward another entity.
-
C.
threatTypeAddressed
Indicates that a given action, measure, or entity is specifically intended to counter or mitigate a particular type of threat.
-
D.
transportThreat
Indicates a relationship where an entity moves or conveys a threat from one place or context to another.
-
E.
endangerment
chosen
Indicates a relationship in which one entity exposes another to potential harm, risk, or danger.
- 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_69a493d6e380819097b384986ffc315c |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b95d35888190a20593a278175df7 |
completed | March 1, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69a4b7276180819085c6b23501a6a6e0 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.