Triple
T1587113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Venta |
E34089
|
entity |
| Predicate | excavatedBy |
P7650
|
FINISHED |
| Object |
Robert Heizer
Robert Heizer was an influential American archaeologist known for his pioneering research on Mesoamerican and Native Californian cultures.
|
E182623
|
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: Robert Heizer | Statement: [La Venta, excavatedBy, Robert Heizer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Heizer Context triple: [La Venta, excavatedBy, Robert Heizer]
-
A.
John Heydler
John Heydler was an American baseball executive who served as president of the National League in the early 20th century.
-
B.
Gerald Hagey
Gerald Hagey was a Canadian academic and administrator best known as the founding president who led the development of the University of Waterloo into a major institution.
-
C.
Gustav Kleikamp
Gustav Kleikamp was a German naval officer and rear admiral in the Kriegsmarine during World War II, known for commanding forces in the opening attack on Poland.
-
D.
Robert Frazen
Robert Frazen is a film editor known for his work on movies such as "Smokin' Aces."
-
E.
George Boemler
George Boemler was a film editor known for his work on classic Hollywood productions, including the musical comedy "High Society."
- 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: Robert Heizer Triple: [La Venta, excavatedBy, Robert Heizer]
Generated description
Robert Heizer was an influential American archaeologist known for his pioneering research on Mesoamerican and Native Californian cultures.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Robert Heizer Target entity description: Robert Heizer was an influential American archaeologist known for his pioneering research on Mesoamerican and Native Californian cultures.
-
A.
John Heydler
John Heydler was an American baseball executive who served as president of the National League in the early 20th century.
-
B.
Gerald Hagey
Gerald Hagey was a Canadian academic and administrator best known as the founding president who led the development of the University of Waterloo into a major institution.
-
C.
Gustav Kleikamp
Gustav Kleikamp was a German naval officer and rear admiral in the Kriegsmarine during World War II, known for commanding forces in the opening attack on Poland.
-
D.
Robert Frazen
Robert Frazen is a film editor known for his work on movies such as "Smokin' Aces."
-
E.
George Boemler
George Boemler was a film editor known for his work on classic Hollywood productions, including the musical comedy "High Society."
- 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_69a885fceb2c8190b47e0f7c0aefbff0 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9090b3a20819098fdb5605ee739d7 |
completed | March 5, 2026, 4:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad51b2b4d4819093f2ae3759838757 |
completed | March 8, 2026, 10:38 a.m. |
| NEDg | Description generation | batch_69ad52b1243c8190b65c1f09ee9e2f02 |
completed | March 8, 2026, 10:42 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad53257d948190ac1dd9071726c9b5 |
completed | March 8, 2026, 10:44 a.m. |
Created at: March 4, 2026, 7:27 p.m.