Triple
T38339748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bat Cave (Hpa-An) |
E1038061
|
entity |
| Predicate | primaryActivityForVisitors |
P76976
|
FINISHED |
| Object | watching bat exodus |
—
|
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: watching bat exodus | Statement: [Bat Cave (Hpa-An), primaryActivityForVisitors, watching bat exodus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryActivityForVisitors Context triple: [Bat Cave (Hpa-An), primaryActivityForVisitors, watching bat exodus]
-
A.
primaryVisitors
Indicates that certain entities are the main or most important visitors associated with another entity or context.
-
B.
primaryVisitorsType
Indicates the main category or type of visitors that predominantly engage with or are targeted by an entity.
-
C.
primaryActivityPattern
Indicates the main recurring type of activity or behavior that characterizes how an entity typically operates or functions.
-
D.
primaryEngagement
chosen
Indicates the main or most significant interaction, involvement, or relationship that an entity has with another entity or activity.
-
E.
typicalVisitorOrigin
Indicates the usual geographic source or location from which visitors to a place, event, or entity most commonly come.
- 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_69f76e20d65c81909619ac0dd85c56f0 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1c850c819088795a7ae59bdeb8 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:30 p.m.