Triple
T36988172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lookin At Lucky |
E915019
|
entity |
| Predicate | notableProgeny |
P50188
|
FINISHED |
| Object |
Lookin At Lee
Lookin At Lee is an American Thoroughbred racehorse best known for finishing second in the 2017 Kentucky Derby.
|
E2207488
|
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: Lookin At Lee | Statement: [Lookin At Lucky, notableProgeny, Lookin At Lee]
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: Lookin At Lee Triple: [Lookin At Lucky, notableProgeny, Lookin At Lee]
Generated description
Lookin At Lee is an American Thoroughbred racehorse best known for finishing second in the 2017 Kentucky Derby.
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_69f76e8dd0408190b8b46da118ea5128 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9ffa7e0008190b620917229e20cb8 |
completed | May 5, 2026, 2:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3e2c52dae4819081c1f0291a849d7d |
completed | June 26, 2026, 7:37 a.m. |
| NEDg | Description generation | batch_6a3e2cf6ae7081909fca0bbf9eeab76b |
completed | June 26, 2026, 7:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a3e490a73a0819098e965f2fb00c3ae |
completed | June 26, 2026, 9:40 a.m. |
Created at: May 3, 2026, 4:14 p.m.