Triple
T18463118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mazatlán Lighthouse |
E451085
|
entity |
| Predicate | hasFoundationOn |
P13223
|
FINISHED |
| Object | natural hill |
—
|
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: natural hill | Statement: [Mazatlán Lighthouse, hasFoundationOn, natural hill]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFoundationOn Context triple: [Mazatlán Lighthouse, hasFoundationOn, natural hill]
-
A.
hasFoundation
chosen
Indicates that an entity is supported, established, or based upon a particular foundation or underlying basis.
-
B.
foundationFoundedIn
Indicates that a foundation was established or came into existence in a specific year or time period.
-
C.
foundedUnder
Indicates that an entity was established or created during the tenure, authority, or jurisdiction of another entity (such as a leader, regime, or governing body).
-
D.
foundedInfrastructure
Indicates that an entity established or created a particular piece of infrastructure, such as a facility, system, or network.
-
E.
foundedFor
Indicates that an entity was established or created specifically to serve, support, or benefit another entity or purpose.
- 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_69d8d38345688190b565eac2e4cd7935 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e52a80a2bc81909ec14811577a311d |
completed | April 19, 2026, 7:18 p.m. |
| PD | Predicate disambiguation | batch_69e469d05cf4819099baf1665a9cf18a |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:33 a.m.