Triple
T36112434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jinshanling |
E1044534
|
entity |
| Predicate | hasWatchtower |
P8955
|
FINISHED |
| Object |
General Tower
General Tower is a prominent watchtower on the Jinshanling section of the Great Wall of China, known for its strategic vantage point and well-preserved architecture.
|
E2170669
|
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: General Tower | Statement: [Jinshanling, hasWatchtower, General Tower]
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: General Tower Triple: [Jinshanling, hasWatchtower, General Tower]
Generated description
General Tower is a prominent watchtower on the Jinshanling section of the Great Wall of China, known for its strategic vantage point and well-preserved architecture.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWatchtower Context triple: [Jinshanling, hasWatchtower, General Tower]
-
A.
hasTower
chosen
Indicates that one entity possesses, contains, or is characterized by the presence of a tower.
-
B.
hasServiceTower
Indicates that an entity is equipped with or associated with a service tower that supports its operation or maintenance.
-
C.
isObservationTower
Indicates that something functions as an observation tower, serving primarily as a structure for viewing or monitoring an area from an elevated position.
-
D.
hasRocketTower
Indicates that an entity possesses or is equipped with a rocket-firing tower structure.
-
E.
hasTowerPosition
Indicates that an entity occupies or is assigned a specific position or location within a tower.
- F. None of above.
Provenance (6 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_69f76e344a4c8190af3858c6d78ba88f |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fbbc49da8c8190902bbb05d2477cab |
completed | May 6, 2026, 10:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a38de0492ec81908bff20b21a6dcc1e |
completed | June 22, 2026, 7:02 a.m. |
| NEDg | Description generation | batch_6a38debb5dec8190bf6b5faa18907623 |
completed | June 22, 2026, 7:05 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a38e299db6481908dda9ad7c048f08e |
completed | June 22, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69fbb13f34b08190bbbb220ac1e6e666 |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:08 p.m.