Triple
T32199359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tianya Haijiao |
E822488
|
entity |
| Predicate | hasRock |
P194563
|
FINISHED |
| Object |
Tianya Stone
Tianya Stone is a famous inscribed coastal rock at the Tianya Haijiao scenic area in Sanya, Hainan, often regarded as a symbolic landmark of “the edge of the earth” in Chinese culture.
|
E1994774
|
NE FINISHED |
How this triple was built (3 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: Tianya Stone | Statement: [Tianya Haijiao, hasRock, Tianya Stone]
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: Tianya Stone Triple: [Tianya Haijiao, hasRock, Tianya Stone]
Generated description
Tianya Stone is a famous inscribed coastal rock at the Tianya Haijiao scenic area in Sanya, Hainan, often regarded as a symbolic landmark of “the edge of the earth” in Chinese culture.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRock Context triple: [Tianya Haijiao, hasRock, Tianya Stone]
-
A.
hasRockRecordIn
Indicates that an entity has a recorded instance or documentation of rock-related data, activity, or presence within a specified context or location.
-
B.
hasRockRecord
Indicates that an entity possesses or is associated with a documented record related to rock music or rock materials.
-
C.
hasRockType
Indicates that an entity is composed of, characterized by, or associated with a specific type of rock.
-
D.
hasRockSequence
Indicates that one entity possesses or is associated with a specific ordered sequence of rocks.
-
E.
hasRockGrade
Indicates that an entity is associated with a specific difficulty or quality grade used to classify rock climbing routes or rock features.
- F. None of above. chosen
Provenance (7 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_69f349093174819086e633c190a51aa8 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd7b0503a08190ba07338365b6fcc9 |
completed | May 8, 2026, 5:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2f0bee92448190b3d550d66ba6cb6b |
completed | June 14, 2026, 8:15 p.m. |
| NEDg | Description generation | batch_6a2f0cf651dc8190b1a2dcb0f74a49c5 |
completed | June 14, 2026, 8:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2f0d81f9b081908d91499b165318cc |
completed | June 14, 2026, 8:22 p.m. |
| PD | Predicate disambiguation | batch_69fd7a9733dc81909199f453c0cc2bc1 |
completed | May 8, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69fd7b042a548190b3abe31bc3258278 |
completed | May 8, 2026, 5:56 a.m. |
Created at: May 1, 2026, 12:36 a.m.