Triple
T2392213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | El Panecillo |
E48967
|
entity |
| Predicate | topType |
P35194
|
FINISHED |
| Object | rounded hilltop |
—
|
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: rounded hilltop | Statement: [El Panecillo, topType, rounded hilltop]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topType Context triple: [El Panecillo, topType, rounded hilltop]
-
A.
headType
Indicates the specific kind or category of head associated with an entity (e.g., type of head part, head role, or head classification in a structure or system).
-
B.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
C.
titleType
Indicates the specific category or kind of title associated with an entity (e.g., whether it is a main title, alternative title, working title, etc.).
-
D.
heads
Indicates that one entity leads, directs, or is in charge of another entity, such as an organization, group, or initiative.
-
E.
peakType
chosen
Indicates the specific classification or category of a peak based on its form, prominence, or other defining characteristics.
- 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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc87587708190a7f2bc473a898bc2 |
completed | March 7, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69abc5a1b5748190b4cd8989700f4dd2 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:57 p.m.