Triple
T3088109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Plain of Jars |
E64422
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Site 52
Site 52 is one of the designated jar-bearing locations within Laos’s Plain of Jars archaeological landscape, known for its clusters of ancient megalithic stone vessels.
|
E326054
|
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: Site 52 | Statement: [Plain of Jars, hasPart, Site 52]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Site 52 Context triple: [Plain of Jars, hasPart, Site 52]
-
A.
Sito
Sito is an epithet of the Greek goddess Demeter that emphasizes her role as the provider of grain and sustenance.
-
B.
Moonhaven
Moonhaven is a science fiction television series set in a utopian lunar colony that becomes central to humanity’s survival.
-
C.
Log Town
Log Town is the historical name for what is now Gaithersburg, a city in Montgomery County, Maryland.
-
D.
Shatterdome
Shatterdome is a massive coastal command and maintenance complex that serves as the operational base for Jaeger mechs and their pilots in the Pacific Rim universe.
-
E.
The Den
The Den is the official student cheering section for UCLA athletics, known for its energetic support at Bruins games, including women's basketball.
- 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: Site 52 Triple: [Plain of Jars, hasPart, Site 52]
Generated description
Site 52 is one of the designated jar-bearing locations within Laos’s Plain of Jars archaeological landscape, known for its clusters of ancient megalithic stone vessels.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Site 52 Target entity description: Site 52 is one of the designated jar-bearing locations within Laos’s Plain of Jars archaeological landscape, known for its clusters of ancient megalithic stone vessels.
-
A.
Sito
Sito is an epithet of the Greek goddess Demeter that emphasizes her role as the provider of grain and sustenance.
-
B.
Moonhaven
Moonhaven is a science fiction television series set in a utopian lunar colony that becomes central to humanity’s survival.
-
C.
Log Town
Log Town is the historical name for what is now Gaithersburg, a city in Montgomery County, Maryland.
-
D.
Shatterdome
Shatterdome is a massive coastal command and maintenance complex that serves as the operational base for Jaeger mechs and their pilots in the Pacific Rim universe.
-
E.
The Den
The Den is the official student cheering section for UCLA athletics, known for its energetic support at Bruins games, including women's basketball.
- 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_69ad857c97d88190b26f9b1c90839c77 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada209fd24819088d887de0a4158f4 |
completed | March 8, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1f8a1fdc48190ae1c2fb9e5198336 |
completed | March 11, 2026, 11:20 p.m. |
| NEDg | Description generation | batch_69b1f9608e88819098f4044e54e0d908 |
completed | March 11, 2026, 11:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b1fe3c8f408190988e7c7e3a51057e |
completed | March 11, 2026, 11:43 p.m. |
Created at: March 8, 2026, 3:03 p.m.