Triple
T17970560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CH2M Hill |
E449327
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Holly Cornell
Holly Cornell was an American engineer and businessman best known as one of the co-founders of the global engineering and construction firm CH2M Hill.
|
E1298634
|
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: Holly Cornell | Statement: [CH2M Hill, foundedBy, Holly Cornell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Holly Cornell Context triple: [CH2M Hill, foundedBy, Holly Cornell]
-
A.
Holly Sutton
Holly Sutton is a popular fictional con artist and adventurer from the soap opera "General Hospital," known for her complex romance with Luke Spencer and her involvement in high-stakes storylines.
-
B.
Holly Sargis
Holly Sargis is the naive teenage narrator and central female protagonist of Terrence Malick’s film "Badlands," whose perspective frames the story’s violent, romantic crime spree.
-
C.
Holly Taylor
Holly Taylor is a Canadian-American actress best known for playing Paige Jennings on the television series "The Americans."
-
D.
Ruby Holbrook
Ruby Holbrook was the wife of acclaimed American actor Hal Holbrook.
-
E.
Marta Robbins
Marta Robbins is a fictional Starfleet lieutenant featured in the Star Trek universe.
- 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: Holly Cornell Triple: [CH2M Hill, foundedBy, Holly Cornell]
Generated description
Holly Cornell was an American engineer and businessman best known as one of the co-founders of the global engineering and construction firm CH2M Hill.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Holly Cornell Target entity description: Holly Cornell was an American engineer and businessman best known as one of the co-founders of the global engineering and construction firm CH2M Hill.
-
A.
Holly Sutton
Holly Sutton is a popular fictional con artist and adventurer from the soap opera "General Hospital," known for her complex romance with Luke Spencer and her involvement in high-stakes storylines.
-
B.
Holly Sargis
Holly Sargis is the naive teenage narrator and central female protagonist of Terrence Malick’s film "Badlands," whose perspective frames the story’s violent, romantic crime spree.
-
C.
Holly Taylor
Holly Taylor is a Canadian-American actress best known for playing Paige Jennings on the television series "The Americans."
-
D.
Ruby Holbrook
Ruby Holbrook was the wife of acclaimed American actor Hal Holbrook.
-
E.
Marta Robbins
Marta Robbins is a fictional Starfleet lieutenant featured in the Star Trek universe.
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b1fa67c48190936f20cea45e4599 |
completed | April 19, 2026, 10:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a033014063c8190be570c12f169f11d |
completed | May 12, 2026, 1:50 p.m. |
| NEDg | Description generation | batch_6a03313620f081909926dea3fc0dd30f |
completed | May 12, 2026, 1:55 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03322540f48190a2957dba3d902003 |
completed | May 12, 2026, 1:59 p.m. |
Created at: April 10, 2026, 10:22 a.m.