Triple
T14645599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bastion of Freedom |
E343839
|
entity |
| Predicate | reflectsReputationAs |
P78687
|
FINISHED |
| Object | center of academic liberty |
—
|
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: center of academic liberty | Statement: [Bastion of Freedom, reflectsReputationAs, center of academic liberty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reflectsReputationAs Context triple: [Bastion of Freedom, reflectsReputationAs, center of academic liberty]
-
A.
denotesReputationOf
chosen
Indicates that one entity represents, expresses, or serves as an indicator of the reputation or perceived standing of another entity.
-
B.
associatedWithReputation
Indicates a relationship where an entity is linked to, influenced by, or characterized in terms of another entity’s reputation or perceived standing.
-
C.
refersToPersonReputation
Indicates that something is about, concerns, or makes reference to a particular person's reputation.
-
D.
hasReputationAmong
Indicates that an entity is regarded or perceived in a particular way by a specified group or audience.
-
E.
haveReputation
Indicates that an entity is recognized or regarded in a certain way by others, reflecting its perceived character, quality, or status.
- 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_69d822e1a2cc81908e5bb93cf61ce3cc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4ea6d8481908e6331ca173c646b |
completed | April 14, 2026, 9:43 p.m. |
| PD | Predicate disambiguation | batch_69de657359c88190b082e3e9f86fc1d7 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:26 a.m.