Triple
T3003867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Longdon |
E81850
|
entity |
| Predicate | nearbyFeature |
P2064
|
FINISHED |
| Object |
Mount Harriet
Mount Harriet is a notable peak in the Falkland Islands that gained prominence as a key location during the 1982 Falklands War.
|
E319436
|
NE FINISHED |
How this triple was built (4 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: Mount Harriet | Statement: [Mount Longdon, nearbyFeature, Mount Harriet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Harriet Context triple: [Mount Longdon, nearbyFeature, Mount Harriet]
-
A.
Mount Catherine
Mount Catherine is the highest mountain in Egypt, located in the southern Sinai Peninsula and known for its rugged terrain and religious significance.
-
B.
Science Hill
Science Hill is a major academic area of Yale University that houses many of the university’s science departments, laboratories, and research facilities.
-
C.
Mount Royal
Mount Royal is a prominent hill and urban park in the heart of Montreal, known as a central natural landmark and namesake of the city.
-
D.
Mount Hollywood
Mount Hollywood is a prominent peak in Los Angeles’ Griffith Park offering panoramic views of the city and the surrounding hills.
-
E.
Butter Hill
Butter Hill is a lesser peak in New York’s Hudson Highlands, known as part of the Storm King Mountain massif overlooking the Hudson River.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Mount Harriet Triple: [Mount Longdon, nearbyFeature, Mount Harriet]
Generated description
Mount Harriet is a notable peak in the Falkland Islands that gained prominence as a key location during the 1982 Falklands War.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mount Harriet Target entity description: Mount Harriet is a notable peak in the Falkland Islands that gained prominence as a key location during the 1982 Falklands War.
-
A.
Mount Catherine
Mount Catherine is the highest mountain in Egypt, located in the southern Sinai Peninsula and known for its rugged terrain and religious significance.
-
B.
Science Hill
Science Hill is a major academic area of Yale University that houses many of the university’s science departments, laboratories, and research facilities.
-
C.
Mount Royal
Mount Royal is a prominent hill and urban park in the heart of Montreal, known as a central natural landmark and namesake of the city.
-
D.
Mount Hollywood
Mount Hollywood is a prominent peak in Los Angeles’ Griffith Park offering panoramic views of the city and the surrounding hills.
-
E.
Butter Hill
Butter Hill is a lesser peak in New York’s Hudson Highlands, known as part of the Storm King Mountain massif overlooking the Hudson River.
- F. None of above. chosen
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_69ad8b1c4de88190a83b7cefaa1f2842 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a149b248190ac4f11afc4871cc1 |
completed | March 8, 2026, 3:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b12e5302c881908294827106b314e4 |
completed | March 11, 2026, 8:56 a.m. |
| NEDg | Description generation | batch_69b12ed522148190b25ad1de42b1604d |
completed | March 11, 2026, 8:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b1d65c9550819081e8734cece6ff13 |
completed | March 11, 2026, 8:53 p.m. |
Created at: March 8, 2026, 2:59 p.m.