Triple
T4329876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Preakness Stakes |
E96720
|
entity |
| Predicate | notableWinner |
P2766
|
FINISHED |
| Object |
Justify
Justify is an American Thoroughbred racehorse best known for winning the 2018 Triple Crown.
|
E431745
|
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: Justify | Statement: [Preakness Stakes, notableWinner, Justify]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Justify Context triple: [Preakness Stakes, notableWinner, Justify]
-
A.
Optimum
Optimum is a telecommunications brand offering cable television, internet, and phone services, primarily in the United States.
-
B.
Grand Justice
Grand Justice is a high-ranking constitutional judge serving on Taiwan’s Judicial Yuan, responsible for interpreting the Constitution and overseeing constitutional matters.
-
C.
Justitia Omnibus
Justitia Omnibus is the Latin motto of Washington, D.C., meaning "Justice for All."
-
D.
Jest
Jest is a popular JavaScript testing framework known for its simplicity, built-in mocking, and snapshot testing, commonly used in Node.js and React applications.
-
E.
The Super
The Super is a 2017 American thriller film about a former cop who becomes the superintendent of a New York City apartment building where tenants begin mysteriously disappearing.
- 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: Justify Triple: [Preakness Stakes, notableWinner, Justify]
Generated description
Justify is an American Thoroughbred racehorse best known for winning the 2018 Triple Crown.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Justify Target entity description: Justify is an American Thoroughbred racehorse best known for winning the 2018 Triple Crown.
-
A.
Optimum
Optimum is a telecommunications brand offering cable television, internet, and phone services, primarily in the United States.
-
B.
Grand Justice
Grand Justice is a high-ranking constitutional judge serving on Taiwan’s Judicial Yuan, responsible for interpreting the Constitution and overseeing constitutional matters.
-
C.
Justitia Omnibus
Justitia Omnibus is the Latin motto of Washington, D.C., meaning "Justice for All."
-
D.
Jest
Jest is a popular JavaScript testing framework known for its simplicity, built-in mocking, and snapshot testing, commonly used in Node.js and React applications.
-
E.
The Super
The Super is a 2017 American thriller film about a former cop who becomes the superintendent of a New York City apartment building where tenants begin mysteriously disappearing.
- 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_69b34542fd908190b11b08faad8decfd |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3513545fc81909e29de7eae1829f7 |
completed | March 12, 2026, 11:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5d09bf304819084fc1b9162c8b48a |
completed | March 14, 2026, 9:18 p.m. |
| NEDg | Description generation | batch_69b5d48a56f881909cc75f45d87c8151 |
completed | March 14, 2026, 9:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5d4f99ff08190957b46cd84954f79 |
completed | March 14, 2026, 9:36 p.m. |
Created at: March 12, 2026, 11:13 p.m.