Triple
T31561520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castle Rock (Stansbury Island summit area) |
E805277
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object |
Castle Rock
Castle Rock is a prominent summit feature on Utah’s Stansbury Island, known as a notable high point in the island’s rugged terrain.
|
E1968576
|
NE 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: Castle Rock | Statement: [Castle Rock (Stansbury Island summit area), hasName, Castle Rock]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Castle Rock Triple: [Castle Rock (Stansbury Island summit area), hasName, Castle Rock]
Generated description
Castle Rock is a prominent summit feature on Utah’s Stansbury Island, known as a notable high point in the island’s rugged terrain.
Provenance (5 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_69f348d22e088190ad555d5bd42f9da0 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a7c864e88190962c372b6bfbec5f |
completed | May 3, 2026, 1:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2b5643ea4c8190b10539fc926c4200 |
completed | June 12, 2026, 12:43 a.m. |
| NEDg | Description generation | batch_6a2b583d06f88190be9d21e20c571568 |
completed | June 12, 2026, 12:52 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2b588d33008190b3bd74c4f638a918 |
completed | June 12, 2026, 12:53 a.m. |
Created at: April 30, 2026, 10:15 p.m.