Triple
T15583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard Yard |
E310
|
entity |
| Predicate | hasAccess |
P273
|
FINISHED |
| Object | gated entrances |
—
|
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: gated entrances | Statement: [Harvard Yard, hasAccess, gated entrances]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAccess Context triple: [Harvard Yard, hasAccess, gated entrances]
-
A.
hasRole
Indicates that an entity occupies, performs, or is assigned a specific role or function in relation to another entity or context.
-
B.
hasScope
Indicates that one entity defines, limits, or encompasses the range, extent, or applicability within which another entity operates or is valid.
-
C.
grantedTo
Indicates that a right, permission, or resource has been formally given or assigned by one party to another.
-
D.
hasPower
Indicates that one entity possesses authority, control, or influence over another entity or over a particular domain or resource.
-
E.
allows
chosen
Indicates that one entity grants permission, capability, or opportunity for another entity to perform an action or be in a certain state.
- 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_69a23d7ad88c8190bffe8ab091d86642 |
completed | Feb. 28, 2026, 12:57 a.m. |
| NER | Named-entity recognition | batch_69a240b249788190af8dbf7e80e9c91b |
completed | Feb. 28, 2026, 1:11 a.m. |
| PD | Predicate disambiguation | batch_69a23feae8c481908d8c50faac01fc5c |
completed | Feb. 28, 2026, 1:07 a.m. |
Created at: Feb. 28, 2026, 1:02 a.m.