Triple
T3516967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Presidio of San Francisco |
E74330
|
entity |
| Predicate | closedAsArmyPostIn |
P16659
|
FINISHED |
| Object | 1994 |
—
|
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: 1994 | Statement: [Presidio of San Francisco, closedAsArmyPostIn, 1994]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closedAsArmyPostIn Context triple: [Presidio of San Francisco, closedAsArmyPostIn, 1994]
-
A.
closedAsActiveArmyPost
chosen
Indicates that a location or facility ceased operations specifically in its role as an active Army post.
-
B.
closedUnder
Indicates that applying a specified operation to elements within a set always produces a result that is also an element of that same set.
-
C.
closedIn
Indicates that one entity is enclosed, contained, or surrounded within the boundaries or limits defined by another entity.
-
D.
closed
Indicates that an entity has brought something (such as an object, container, or space) from an open state into a shut or sealed state, or that it is currently in that shut state.
-
E.
closedBy
Indicates that one entity performs the action of closing, finishing, or terminating another entity (such as a task, issue, or process).
- 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_69ad85cfb5c881909c9a2edd9d6043cc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc31c0688190a890621a901f5f5f |
completed | March 8, 2026, 6:13 p.m. |
| PD | Predicate disambiguation | batch_69adae10689c8190b7dc6d7daa8295b6 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:19 p.m.