Triple
T30603041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeffrey Harrington |
E778963
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object |
Gavin Houston
Gavin Houston is an American actor best known for his roles on soap operas such as "Guiding Light" and the primetime drama "The Haves and the Have Nots."
|
E1922028
|
NE FINISHED |
How this triple was built (2 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: Gavin Houston | Statement: [Jeffrey Harrington, portrayedBy, Gavin Houston]
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: Gavin Houston Triple: [Jeffrey Harrington, portrayedBy, Gavin Houston]
Generated description
Gavin Houston is an American actor best known for his roles on soap operas such as "Guiding Light" and the primetime drama "The Haves and the Have Nots."
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_69f224a21fc08190abd9d8dd9eb6bb4c |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f689b36a888190b139d35c8c5d88bd |
completed | May 2, 2026, 11:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a28571d5ce081909739cb3cbb4d729b |
completed | June 9, 2026, 6:10 p.m. |
| NEDg | Description generation | batch_6a28597516d481909ebbcd3d2554e7ae |
completed | June 9, 2026, 6:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a285a60386081909c73d1ef55aaeb8a |
completed | June 9, 2026, 6:24 p.m. |
Created at: April 29, 2026, 8:25 p.m.