Triple
T16970798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Litten Tree (Salisbury) |
E411670
|
entity |
| Predicate | knownAs |
P39
|
FINISHED |
| Object |
Litten Tree
Litten Tree is a public house and social venue in Salisbury, England, known locally by that name.
|
E1243152
|
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: Litten Tree | Statement: [Litten Tree (Salisbury), knownAs, Litten Tree]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Litten Tree Context triple: [Litten Tree (Salisbury), knownAs, Litten Tree]
-
A.
Bent Tree
Bent Tree is a residential neighborhood located within the suburban community of Burke in Fairfax County, Virginia.
-
B.
Fern Tree
Fern Tree is a small bushland suburb on the slopes of Mount Wellington near Hobart, Tasmania, known for its forested setting and walking tracks.
-
C.
Whitetree
Whitetree is a small, ancient wildling village in the far north of Westeros, notable for the enormous weirwood tree at its center.
-
D.
Treene
The Treene is a river in northern Germany that flows through the state of Schleswig-Holstein and ultimately drains into the Eider River.
-
E.
The Big Tree
The Big Tree is a famous, centuries-old yellowwood tree near Hogsback in South Africa, known as a popular natural landmark for visitors and hikers.
- 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: Litten Tree Triple: [Litten Tree (Salisbury), knownAs, Litten Tree]
Generated description
Litten Tree is a public house and social venue in Salisbury, England, known locally by that name.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Litten Tree Target entity description: Litten Tree is a public house and social venue in Salisbury, England, known locally by that name.
-
A.
Bent Tree
Bent Tree is a residential neighborhood located within the suburban community of Burke in Fairfax County, Virginia.
-
B.
Fern Tree
Fern Tree is a small bushland suburb on the slopes of Mount Wellington near Hobart, Tasmania, known for its forested setting and walking tracks.
-
C.
Whitetree
Whitetree is a small, ancient wildling village in the far north of Westeros, notable for the enormous weirwood tree at its center.
-
D.
Treene
The Treene is a river in northern Germany that flows through the state of Schleswig-Holstein and ultimately drains into the Eider River.
-
E.
The Big Tree
The Big Tree is a famous, centuries-old yellowwood tree near Hogsback in South Africa, known as a popular natural landmark for visitors and hikers.
- 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_69d886ca8f348190812768ea8d5055ce |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d0ac23a48190992fa125fceb1eb2 |
completed | April 18, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d471d4248190acf40b6c11926a65 |
completed | May 10, 2026, 6:54 p.m. |
| NEDg | Description generation | batch_6a00d503f4f08190a0dcdb050d5bc7a3 |
completed | May 10, 2026, 6:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00d5adee908190a13bfc765e7c8f06 |
completed | May 10, 2026, 6:59 p.m. |
Created at: April 10, 2026, 5:31 a.m.