Triple
T19144297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Leigh |
E468638
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Randomistas
Randomistas is a book by economist and politician Andrew Leigh that explores how randomized controlled trials are used to evaluate policies and improve decision-making in fields like economics, medicine, and public policy.
|
E1360685
|
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: Randomistas | Statement: [Andrew Leigh, notableWork, Randomistas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Randomistas Context triple: [Andrew Leigh, notableWork, Randomistas]
-
A.
Rand
Rand is a small rural locality in New South Wales, Australia, situated within the jurisdiction of the Urana Shire Council.
-
B.
Rand
Rand is a masculine given name, often used as a short form of Randall or Randolph.
-
C.
Libertini
Libertini is an Italian-origin surname most notably associated with American character actor Richard Libertini.
-
D.
Radicale
Radicale is a lightweight, open-source CalDAV and CardDAV server designed for simple calendar and contact synchronization.
-
E.
The Random
The Random is a character from the webcomic "Insomnia," likely embodying chaotic or unpredictable elements within the story’s narrative.
- 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: Randomistas Triple: [Andrew Leigh, notableWork, Randomistas]
Generated description
Randomistas is a book by economist and politician Andrew Leigh that explores how randomized controlled trials are used to evaluate policies and improve decision-making in fields like economics, medicine, and public policy.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Randomistas Target entity description: Randomistas is a book by economist and politician Andrew Leigh that explores how randomized controlled trials are used to evaluate policies and improve decision-making in fields like economics, medicine, and public policy.
-
A.
Rand
Rand is a masculine given name, often used as a short form of Randall or Randolph.
-
B.
Rand
Rand is a small rural locality in New South Wales, Australia, situated within the jurisdiction of the Urana Shire Council.
-
C.
Libertini
Libertini is an Italian-origin surname most notably associated with American character actor Richard Libertini.
-
D.
Radicale
Radicale is a lightweight, open-source CalDAV and CardDAV server designed for simple calendar and contact synchronization.
-
E.
The Random
The Random is a character from the webcomic "Insomnia," likely embodying chaotic or unpredictable elements within the story’s narrative.
- 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e977fa208190aa8cafd0966599c6 |
completed | April 20, 2026, 8:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a06f24e34c4819090954c2b79ab20bb |
completed | May 15, 2026, 10:15 a.m. |
| NEDg | Description generation | batch_6a06f366e514819080de839bdde22fc2 |
completed | May 15, 2026, 10:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a06f4039ca881908679e5da604eea50 |
completed | May 15, 2026, 10:22 a.m. |
Created at: April 10, 2026, 12:06 p.m.