Triple
T21536813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Replicas |
E531369
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Mark Gao
Mark Gao is a film producer known for his work on the science fiction thriller "Replicas."
|
E1489364
|
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: Mark Gao | Statement: [Replicas, producer, Mark Gao]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Gao Context triple: [Replicas, producer, Mark Gao]
-
A.
John Hao
John Hao is an athlete who emerged from Saint Louis School’s sports program.
-
B.
Marcus Chong
Marcus Chong is an American actor best known for his role as Tank in the science fiction film "The Matrix."
-
C.
Garrett Wang
Garrett Wang is an American actor best known for playing Ensign Harry Kim on the television series Star Trek: Voyager.
-
D.
Andrew Kuan
Andrew Kuan is a Singaporean businessman and former public figure known for his involvement in corporate governance and a high-profile, but ultimately unsuccessful, bid to run for the Singapore presidency.
-
E.
Harvey Dong
Harvey Dong is an Asian American activist, scholar, and former member of the Asian American Political Alliance known for his role in the Asian American Movement and his work documenting Asian American history.
- 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: Mark Gao Triple: [Replicas, producer, Mark Gao]
Generated description
Mark Gao is a film producer known for his work on the science fiction thriller "Replicas."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mark Gao Target entity description: Mark Gao is a film producer known for his work on the science fiction thriller "Replicas."
-
A.
John Hao
John Hao is an athlete who emerged from Saint Louis School’s sports program.
-
B.
Marcus Chong
Marcus Chong is an American actor best known for his role as Tank in the science fiction film "The Matrix."
-
C.
Garrett Wang
Garrett Wang is an American actor best known for playing Ensign Harry Kim on the television series Star Trek: Voyager.
-
D.
Andrew Kuan
Andrew Kuan is a Singaporean businessman and former public figure known for his involvement in corporate governance and a high-profile, but ultimately unsuccessful, bid to run for the Singapore presidency.
-
E.
Harvey Dong
Harvey Dong is an Asian American activist, scholar, and former member of the Asian American Political Alliance known for his role in the Asian American Movement and his work documenting Asian American history.
- 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee9d0e5a9c8190894ec3666d3296aa |
completed | April 26, 2026, 11:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09e835fd08819098fde7600d5c91d6 |
completed | May 17, 2026, 4:09 p.m. |
| NEDg | Description generation | batch_6a09e909a4888190aa1d704eb157d86d |
completed | May 17, 2026, 4:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09ea119664819081b072c892fc0471 |
completed | May 17, 2026, 4:17 p.m. |
Created at: April 16, 2026, 6:27 p.m.