Triple
T3220270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Round Tower |
E67494
|
entity |
| Predicate | hasObservationFacility |
P46591
|
FINISHED |
| Object | telescope |
—
|
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: telescope | Statement: [Round Tower, hasObservationFacility, telescope]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasObservationFacility Context triple: [Round Tower, hasObservationFacility, telescope]
-
A.
hasObservationSite
Indicates that something (such as a measurement, event, or observation activity) is associated with or took place at a specific observation site or location.
-
B.
hasObservation
Indicates that an entity records, contains, or is associated with a specific observation or measured instance.
-
C.
hasNearbyObservatories
Indicates that one entity has one or more observatories located in close geographic proximity to it.
-
D.
hasDiscoveryFacility
Indicates that an entity has, is associated with, or is served by a facility where discoveries (such as scientific, medical, or technological findings) are made or were made.
-
E.
isObservedIn
Indicates that something (such as a phenomenon, property, or behavior) is detected, recorded, or found to occur within a particular context, setting, or environment.
- F. None of above. chosen
Provenance (4 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_69ad858b8adc8190ad989712c87a476b |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adae16f20081909d7f3bac016f961d |
completed | March 8, 2026, 5:12 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0bb6c48190a0659c67d40ee37c |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada148e9108190b363dd0f1a94ac8e |
completed | March 8, 2026, 4:18 p.m. |
Created at: March 8, 2026, 3:08 p.m.